*This resource is partly funded by the EU research project Envisage where Memkite is a case study*

Maintainer: Amund Tveit – amund@memkite.com

## DeepLearning.University – Abstract

DeepLearning.University is an annotated bibliography of recent publications (2014-2015) related to Deep Learning. If you have suggestions to improvements of this bibliography please send us an email or make your changes as a pull request on the corresponding git project at https://github.com/memkite/DeepLearningBibliography

## Links to Deep Learning Subtopics

[2d] [3d] [acoustic] [acoustic model] [action recognition] [action recognitionx] [action selection] [activation functions] [activity detection] [activity recognition] [adaptive] [ads] [adversarial nets] [adversarial networks] [advertising] [age estimation] [aircraft detection] [algorithm] [algorithms] [alzheimer’s] [animal identification] [applications] [approximate] [architecture] [articulatory synthesis] [asthma] [asynchronous][auto-encoder] [autoencoder] [autogression] [autonomous] [autonomously] [autoregression] [back propagation] [bacteria] [barcode detection] [batch] [batch normalization] [batchwise] [bayes] [bayesian] [behavior model] [behavior models] [belief propagation networks] [bengio] [bifurcated deep network] [big] [big data] [big-data] [bing challenge] [bioinformatics] [biologically] [biology] [bird] [blstm] [boosted] [boosting] [bootstrapping] [brain] [brain waves] [caffe] [calibration] [cancer] [car detection] [cartography] [cascade] [cell] [challenges] [character recognition] [chinese] [classification] [click-through] [cloud] [clustered] [clustering] [cnn] [coding scheme] [cognition] [cognitive] [collaborative filtering] [combinatorical optimization] [compression] [computer vision] [concept learning] [consistency] [constrained] [constructive neural networks] [content-based] [contour detection] [controller] [convex] [convex optimization] [convexity] [convnet] [convnets] [convoluational neural network] [convolutional] [convolutional network] [convolutional networks] [convolutional neural network] [convolutional neural networks] [corpora] [cortical processing] [ct] [data center] [data mining] [data-parallel] [dataset] [dcnn] [decision making] [decision tree] [deep belief nets] [deep belief network] [deep boltzmann machines] [deep convex networks] [deep learning] [deep neural network] [deep sigmoid belief networks] [deeply-supervised nets] [deformation] [deformations] [demodulation] [denoising] [depression] [depth estimation] [depth-videos] [dermatology] [devops] [diabetes] [diabetic] [diacritization] [dictionary] [dictionary extraction] [digit classification] [digit recognition] [disambiguation] [discriminative] [discriminative learning] [disease] [disjunctive] [distance functions] [distributed] [distributed system] [dnn] [domain invariance] [domain-adversarial] [drone] [dropout] [drug] [drug target detection] [economy] [edge detection] [education] [eeg] [electricity] [electricity forecast] [embedded] [emotion] [emotion detection] [encoding] [encryption] [energy] [energy efficiency] [energy efficient] [ensemble learning] [entities] [entity] [error correction] [estimation] [evaluation] [event] [event detection] [examination] [experimental] [extreme learning] [eye detection] [eye tracking] [face] [face detection] [face expression analysis] [face recognition] [facial] [factorization] [fault diagnosis] [feature] [feature discovery] [feature encoding] [feature extraction] [feature recognition] [feature representation] [feature selection] [feature tuning] [features] [filtering] [finance] [fine tuning] [fine-tuning] [fingerprint detection] [fingerprint recognition] [fisher vectors] [fmri] [food detection] [fpga] [fpga-based] [framework] [freehand] [frequency domain] [fuzzy learning] [galaxy] [game] [games] [gaussian] [generative] [generative deep learning] [genetic programming] [gesture] [gesture recognition] [go] [googlenet] [gpu] [gradient] [gradient-based] [graph] [graphical model] [graphics] [graphs] [grasping system] [hadoop] [hand pose] [handwriting recognition] [handwritten] [handwritten recognition] [hardware] [hash] [hashing] [healthcare] [hearing aid] [heart failure] [helicopter] [hessian] [hierarchical] [high-dimensional data] [hmax] [hmm] [hmm-based] [hough transform] [human behavior] [human pose] [human-level] [hyperspectral] [image classification] [image de-noising] [image parsing] [image quality] [image recognition] [image recognitionx] [image representation] [image segmentation] [imagery] [imaging] [improvisation] [indexing] [induction] [inductive bias] [information] [information retrieval] [information theory] [information-theoretic] [infrastructure] [interpolation] [invariant] [javascript] [kernel] [kernel methods] [kernels] [kickback] [labeling] [lasso] [latent structure] [lattice] [learning to rank] [lecun] [lfw] [linear model] [linear models] [log-likelihood] [logistic] [long short-term memory] [low resolution] [lstm] [machine translation] [mahout] [mammogram analysis] [manufacturing] [matrix] [max pooling] [medical] [medical records] [medicine] [memory] [memristor] [metric] [metric learning] [microblog] [mimd] [mine detection] [missing] [mobile] [monte carlo] [motion] [motion detection] [motion recognition] [mri] [multi-label] [multicore] [multimedia] [multimodal] [music] [natural language processing] [network] [network analysis] [network congestion] [networking] [neuromorphic] [neuron] [neuroscience] [newton] [noise] [noiseness] [noisy] [noisy data] [non-convex] [non-euclidian] [numerical] [numerics] [object classification] [object detection] [object localization] [object recognition] [object reconstruction] [occlusion] [occlusions] [online learning] [open source] [optimization] [optimized] [orientation estimation] [over-sampling] [overview] [pancreas] [parallel] [parallelization] [parameter] [parameter tuning] [parameters] [parsing] [part-of-speech] [pca] [pedestrian detection] [perception] [perceptron] [performance improvement] [personalize] [phoneme] [photo adjustment] [photonic] [physics] [pinterest] [plankton] [planning] [platform] [pooling] [pose] [pose recognition] [posture recognition] [pre-training] [predicting] [prediction] [predictive modelling] [predictors] [pretraining] [probabilistic] [processor] [programming language processing] [prosthetics] [proteinomics] [python] [quality] [quantum] [quantum computing] [quantum deep learning] [random field] [random fields] [random forests] [ranking] [rbm] [recommendation systems] [recommender systems] [rectified] [rectifiers] [rectifiers:] [recurrant neural networks] [recurrent] [recurrent nets] [recurrent networks] [recurrent neural networks] [regression] [regularization] [reinforcement learning] [reliability] [representation] [representation learning] [restricted boltzmann machine] [restricted boltzmann machines] [restricted bolzmann machines] [retail] [retinal images] [reverse annealing] [review] [risk minimization] [road detection] [robot] [robotics] [robust] [salient] [sampling] [sar data] [scalability] [scene classification] [scene recognition] [scheduling] [score function] [sda] [search] [security] [segmentation] [self-informed] [semantic] [semantic indexing] [semantics] [semantix indexing] [semi-supervised] [sensor data] [sensory] [sentiment] [sentiment analysis] [sequence learning] [sequence modelling] [shape classification] [shearlet transform] [sigmoid] [sign language] [signal processing] [similarity learning] [simplicity] [simulation] [singular value decomposition] [sketch recognition] [smart city] [smart homes] [smoothing] [social] [social network] [soft computing] [softmax] [software] [sosial network] [sound] [sound retrieval] [spam] [sparse] [sparseness] [sparsity] [spatial] [spatial planning] [spatially] [spatio-temporal] [spectral] [spectral classification] [speech] [speech recognition] [speech synthesis] [stability] [statistical inference] [stochastic] [stochastic gradient] [stochastic gradient descent] [stochastic optimization] [strategiesx] [structured networks] [study] [subspace analysis] [subspace learning] [summarization] [supervised] [supervised learning] [support vector machine] [support vector machines] [surrogates] [survey] [svm] [swarm optimization] [synonym extraction] [target coding] [target detection] [temporal] [temporal dependencies] [tensor] [term] [text classification] [text recognition] [texture recognition] [theano] [theory] [thermodynamics] [thin deep networks] [time series] [tongue] [tool] [tools] [topic modelling] [traffic] [traffic prediction] [traffic sign] [transcription] [transductive] [transfer learning] [tree structure] [tree structures] [trends] [twitter] [ultrasound] [una] [unsupervised] [unsupervised learning] [user authentication] [user interface] [user interfaces] [vehicle] [vehicle classification] [vehicle classificationx] [vehicle recognition][videos] [vision] [visual] [visual memory] [vocal] [voice recognition] [vowel] [weather prediction] [web mining] [web search] [web spam] [weed classification] [weld] [wind power] [word embeddings] [word segmentation] [word sense]

## 2D

- Optimized multi-channel deep neural network with 2d graphical representation of acoustic speech features for emotion recognition
- Dense 3d Face Alignment from 2d Videos in Real-Time

## 3D

- A deep learning approach to the classification of 3D CAD models
- 3d object retrieval with stacked local convolutional autoencoder
- Deep Learning Representation using Autoencoder for 3d Shape Retrieval
- Local deep feature learning framework for 3d shape
- Human gesture recognition using three-dimensional integral imaging
- Indirect shape analysis for 3d shape retrieval
- Supervised feature learning via â„“2-norm regularized logistic regression for 3d object recognition
- A 3d model recognition mechanism based on deep boltzmann machines
- Combining heterogenous features for 3d hand-held object recognition
- Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2d and 3d Images
- A comparison of 3d shape retrieval methods based on a large-scale benchmark supporting multimodal queries
- Deep Learning For Objective Quality Assessment Of 3d Images
- Designing Deep Networks for Surface Normal Estimation
- TriViews: A general framework to use 3d depth data effectively for action recognition
- High-definition 3d Image Processing Technology for Ultrasound Diagnostic Scanners
- C3d: Generic Features for Video Analysis
- Semantic Volume Segmentation with Iterative Context Integration
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Inferring 3d Object Pose in Rgb-d Images
- Dense 3d Face Alignment from 2d Videos in Real-Time
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Fitting 3d Morphable Models using Local Features
- 18.1 A 2.71 nJ/pixel 3D-stacked gaze-activated object-recognition system for low-power mobile Hmd applications
- 3d Convolutional Neural Networks for Landing Zone Detection from LiDAR
- Iterative 3d shape classification by online metric learning

## Acoustic

- Implementation of Dnn-hmm Acoustic Models for Phoneme Recognition
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Optimized multi-channel deep neural network with 2d graphical representation of acoustic speech features for emotion recognition
- Improving acoustic model for English Asr System using deep neural network
- Deep Neural Networks for Acoustic Modeling

## Acoustic Model

- Implementation of Dnn-hmm Acoustic Models for Phoneme Recognition
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Improving acoustic model for English Asr System using deep neural network
- Deep Neural Networks for Acoustic Modeling

## Action Recognition

- Action Recognition Using Hierarchical Independent Subspace Analysis with Trajectory
- Learning spatio-temporal features for action recognition from the side of the video
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks
- Human Interaction Recognition Using Independent Subspace Analysis Algorithm
- Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach

## Action Recognitionx

## Action Selection

## Activation Functions

## Activity Detection

## Activity Recognition

## Adaptive

- Adaptive Road Detection via Context-aware Label Transfer
- RMSProp and equilibrated adaptive learning rates for non-convex optimization
- Dynamic Feature-Adaptive Subdivision
- Deep Neural Programs for Adaptive Control in Cyber-Physical Systems
- Unsupervised domain adaptation via representation learning and adaptive classifier learning

## Ads

## Adversarial Nets

## Adversarial Networks

## Advertising

## Age Estimation

## Aircraft Detection

## Algorithm

- Mean-normalized stochastic gradient for large-scale deep learning
- Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning
- Deep process neural network for temporal deep learning
- On the Equivalence Between Deep NADE and Generative Stochastic Networks
- Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
- Manifold Regularized Deep Neural Networks
- Deep Epitomic Convolutional Neural Networks
- A Winner-Take-All Method for Training Sparse Convolutional Autoencoders
- Analyzing noise in autoencoders and deep networks
- CNN: Single-label to Multi-label
- A comparison of dropout and weight decay for regularizing deep neural networks
- Feed Forward Pre-training for Recurrent Neural Network Language Models
- Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
- On the saddle point problem for non-convex optimization
- Dropout: A Simple Way to Prevent Neural Networks from Overfitting
- Reweighted Wake-Sleep
- Learning Separable Filters
- Karush-Kuhn-Tucker meets David Hubel and Torsten Weisel through Gabriel Kreiman and Andrew Ng: A connection between highlights of constrained convex..
- Learning Deep Representations via Extreme Learning Machines
- Recognizing human activity in smart home using deep learning algorithm
- Going Deeper with Convolutions
- Parallel batch pattern training algorithm for deep neural network
- Improved Perception-Based Spiking Neuron Learning Rule for Real-Time User Authentication
- Unsupervised Domain Adaptation by Backpropagation
- Zero-Shot Learning with Structured Embeddings
- Autoencoder Trees
- Classifying Gray-scale Sar Images: Adeep Learning Approach
- Maximum Reconstruction Probability Training Of Restricted Boltzmann Machines With Auxiliary Function Approach
- Deep Sequential Neural Network
- Finding quasi core with simulated stacked neural networks
- Understanding Locally Competitive Networks
- Accuracy evaluation of deep belief networks with fixed-point arithmetic
- On the Computational Efficiency of Training Neural Networks
- SimNets: A Generalization of Convolutional Networks
- Semantics of Visual Discrimination
- Temporal Coherence in Energy-based Deep Learning Machines for Action Recognition
- The Potential Energy of an Autoencoder
- Enhanced Higgs to $\ tau^+\ tau^-$ Searches with Deep Learning
- A Simple Stochastic Algorithm for Structural Features Learning
- Meta-parameter free unsupervised sparse feature learning
- On the Link Between Gaussian Homotopy Continuation and Convex Envelopes
- Coarse-to-Fine Minimization of Some Common Nonconvexities
- A Method For Extracting Information From The Web Using Deep Learning Algorithm
- Adaptive Information-Theoretical Feature Selection for Pattern Classification
- Stacked Extreme Learning Machines
- The atoms of neural computation
- On The Dynamical Nature Of Computation
- Greedy Approaches to Semi-Supervised Subspace Learning
- Low Rank Tensor Manifold Learning
- Random feedback weights support learning in deep neural networks
- Temporal Dropout of Changes Approach to Convolutional Learning of Spatio-Temporal Features
- A new algorithm on variable-rate convolutional broadcast for network coding in cyclic networks
- Identification and Elucidation of Expression Quantitative Trait Loci (eQTL) and their regulating mechanisms using Decodive Deep Learning
- Dynamic Background Learning through Deep Auto-encoder Networks
- Bimmer: a novel algorithm for detecting differential Dna methylation regions from MBDCap-seq data
- Set-label modeling and deep metric learning on person re-identification
- Stacked Quantizers for Compositional Vector Compression
- SelfieBoost: A Boosting Algorithm for Deep Learning
- Toward a Universal Cortical Algorithm: Examining Hierarchical Temporal Memory in Light of Frontal Cortical Function
- Supervised non-negative matrix factorization for audio source separation
- Multiscale Centerline Detection
- A Convex Formulation for Spectral Shrunk Clustering
- Efficient Benchmarking of Hyperparameter Optimizers via Surrogates
- The Loss Surface of Multilayer Networks
- Cross-Modal Learning via Pairwise Constraints
- An Algorithm of Quantum Restricted Boltzmann Machine Network Based on Quantum Gates and Its Application
- Support Vector-Based Algorithms with Weighted Dynamic Time Warping Kernel Function for Time Series Classification
- Online Bandit Learning for a Special Class of Non-convex Losses
- A twice face recognition algorithm
- Implementation of Evolutionary Algorithms for Deep Architectures
- Stochastic Descent Analysis of Representation Learning Algorithms
- Preliminary evaluation of hyperopt algorithms on HPOLib
- Class Margins: Learning to (Un) Learn
- Accelerated gradient temporal difference learning algorithms
- An Improved Bilinear Deep Belief Network Algorithm for Image Classification
- The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid
- Exploring Latent Structure in Data: Algorithms and Implementations
- Human Interaction Recognition Using Independent Subspace Analysis Algorithm
- Fuzzy Restricted Boltzmann Machine and Its Fast Learning Algorithm
- Cascade object detection with complementary features and algorithms
- Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
- Study on Binary Multilayer Neural Networks with Ebp Algorithm on Image Classification

## Algorithms

## Alzheimer’S

- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Detection of Alzheimer’s disease using group lasso SVM-based region selection

## Animal Identification

## Applications

- Mariana: Tencent Deep Learning Platform and its Applications
- Polypharmacology Modelling Using Proteochemometrics (pcm): Recent Methodological Developments, Applications to Target Families, and Future Prospects
- Traffic Flow Prediction With Big Data: A Deep Learning Approach
- Non-parametric Bayesian Learning with Deep Learning Structure and Its Applications in Wireless Networks
- Log-Linear Models, Extensions and Applications
- Machine Learning for Medical Applications
- Extreme learning machines: new trends and applications
- Extreme learning machines: new trends and applications
- An Overview of Color Name Applications in Computer Vision
- Deep learning applications and challenges in big data analytics
- 4.6 A1. 93tops/w scalable deep learning/inference processor with tetra-parallel Mimd architecture for big-data applications
- 18.1 A 2.71 nJ/pixel 3D-stacked gaze-activated object-recognition system for low-power mobile Hmd applications
- Multithreshold Entropy Linear Classifier: Theory and Applications

## Approximate

- Single image super-resolution by approximated Heaviside functions
- Optimizing Neural Networks with Kronecker-factored Approximate Curvature

## Architecture

- Supervised deep learning with auxiliary networks
- Analysis of Deep Convolutional Neural Network Architectures
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Learning Deep and Wide: A Spectral Method for Learning Deep Networks
- A Generalized Scalable Software Architecture for Analyzing Temporally Structured Big Data in the Cloud
- A Fully Pipelined FPGA Architecture of a Factored Restricted Boltzmann Machine Artificial Neural Network
- Project Adam: Building an Efficient and Scalable Deep Learning Training System
- Unsupervised Feature Learning For Bootleg Detection Using Deep Learning Architectures
- Proposal for a Deep Learning Architecture for Activity Recognition
- Unisense: A Unified and Sustainable Sensing and Transport Architecture for Large Scale and Heterogeneous Sensor Networks
- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
- Da-ccd: A novel action representation by deep architecture of local depth feature
- Review of Advances in Neural Networks: Neural Design Technology Stack
- An Adaptive Stacked Denoising Auto-Encoder Architecture for Human Action Recognition
- Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Application and Architecture of Power Dispatching & Distribution System Using Big Data Technology
- Implementation of Evolutionary Algorithms for Deep Architectures
- Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures
- Obtaining Cross-modal Similarity Metric with Deep Neural Architecture
- Hierarchical reinforcement learning in a biologically plausible neural architecture
- Scene Recognition by Manifold Regularized Deep Learning Architecture
- Recognizing Multi-view Objects with Occlusions using a Deep Architecture
- Universal Memory Architectures for Autonomous Machines
- Deep Learning Framework with Confused Sub-Set Resolution Architecture for Automatic Arabic Diacritization
- A Minimal Architecture for General Cognition
- 4.6 A1. 93tops/w scalable deep learning/inference processor with tetra-parallel Mimd architecture for big-data applications
- A Hierarchical Neuro-Fuzzy Architecture for Human Behavior Analysis

## Articulatory Synthesis

## Asthma

## Asynchronous

- Distributed Asynchronous Optimization of Convolutional Neural Networks
- Asynchronous stochastic optimization for sequence training of deep neural networks
- Distributed Asynchronous Optimization of Convolutional Neural Networks
- Contour Motion Estimation for Asynchronous Event-Driven Cameras
- Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent

## Audio

- Improved audio features for large-scale multimedia event detection
- Single Channel Source Separation with General Stochastic Networks
- Chord Recognition with Stacked Denoising Autoencoders
- A Deep Neural Network Approach to Automatic Birdsong Recognition
- Unsupervised Feature Learning for Audio Classification using Convolutional Deep Belief Networks
- Automated intelligent system for sound signalling device quality assurance
- Neural Network Based Pitch Tracking In Very Noisy Speech
- Prosodic, spectral and voice quality feature selection using a long-term stopping criterion for audio-based emotion recognition
- Supervised non-negative matrix factorization for audio source separation
- Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition
- Convolutional Data: Towards Deep Audio Learning from Big Data
- Physiologic Audio Fingerprinting

## Auto-Encoder

- Dynamic Background Learning through Deep Auto-encoder Networks
- Topic-aware Deep Auto-encoders (tda) for Face Alignment
- An Adaptive Stacked Denoising Auto-Encoder Architecture for Human Action Recognition

## Autoencoder

- DEEP LEARNING VIA STACKED SPARSE AUTOENCODERS FOR AUTOMATED VOXEL-WISE BRAIN PARCELLATION BASED ON FUNCTIONAL CONNECTIVITY (Thesis format: Monograph)
- Analyzing noise in autoencoders and deep networks
- Improving Transfer Learning Accuracy by Reusing Stacked Denoising Autoencoders
- Alternate Layer Sparsity and Intermediate Fine-tuning for Deep Autoencoders
- Effective Multi-Modal Retrieval based on Stacked Auto-Encoders
- Scheduled denoising autoencoders
- AN AUTOENCODER WITH BILINGUAL SPARSE FEATURES FOR IMPROVED STATISTICAL MACHINE TRANSLATION
- Static hand gesture recognition using stacked Denoising Sparse Autoencoders
- 3d object retrieval with stacked local convolutional autoencoder
- Chord Recognition with Stacked Denoising Autoencoders
- Deep Learning Representation using Autoencoder for 3d Shape Retrieval
- Autoencoder Trees
- Deep Directed Generative Autoencoders
- Feature Learning from Incomplete Eeg with Denoising Autoencoder
- The Potential Energy of an Autoencoder
- Auto-encoding Variational Bayes
- Recognition of Handwritten Characters in Chinese Legal Amounts by Stacked Autoencoders
- Improving generation performance of speech emotion recognition by denoising autoencoders
- Stacked Extreme Learning Machines
- Cross-modal Retrieval with Correspondence Autoencoder
- Relational Stacked Denoising Autoencoder for Tag Recommendation
- Learning Feature Representations with a Cost-Relevant Sparse Autoencoder
- Introduction to Autoencoders
- Multimodal Video Classification with Stacked Contractive Autoencoders
- Training Stacked Denoising Autoencoders for Representation Learning
- Made: Masked Autoencoder for Distribution Estimation
- Convergence of gradient based pre-training in Denoising autoencoders
- Denoising Autoencoders for fast Combinatorial Black Box Optimization
- Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder
- Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder

## Autogression

## Autonomous

- Universal Memory Architectures for Autonomous Machines
- Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning â€¦

## Autonomously

## Autoregression

## Back Propagation

- Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics
- Kickback cuts Backprop’s red-tape: Biologically plausible credit assignment in neural networks
- Momentum Effects on Back-Propagation Learning in a Multi-Layer Feed-Forward Neural Network

## Bacteria

## Barcode Detection

## Batch

- Efficient batchwise dropout training using submatrices
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

## Batch Normalization

## Batchwise

## Bayes

## Bayesian

- A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis
- Bayesian Deep Deconvolutional Learning
- Interactions Between Gaussian Processes and Bayesian Estimation
- Towards Building Deep Networks with Bayesian Factor Graphs
- Scalable Bayesian Optimization Using Deep Neural Networks

## Behavior Model

## Behavior Models

## Belief Propagation Networks

## Bengio

- How transferable are features in deep neural networks?
- Handwritten Digits Classification
- Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
- Show and Tell: A Neural Image Caption Generator
- Unsupervised Learning of Semantics of Object Detections for Scene Categorization
- End-to-end Continuous Speech Recognition using Attention-based Recurrent Nn: First Results
- Deep Learning
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Supplementary Material: On the Number of Linear Regions of Deep Neural Networks
- Low precision arithmetic for deep learning
- Adasecant: Robust Adaptive Secant Method for Stochastic Gradient

## Bifurcated Deep Network

## Big

- Random Bits Regression: a Strong General Predictor for Big Data
- Deep learning of fMRI big data: a novel approach to subject-transfer decoding
- Hypothesis Testing with Kernel Embeddings on Big and Interdependent Data
- Computing brains: neuroscience, machine intelligence and big data in the cognitive classroom
- Masterarbeit: Big Data and Machine Learning: A Case Study with Bump Boost
- Promises and Challenges of Big Data Computing in Health Sciences
- Deep learning applications and challenges in big data analytics
- 4.6 A1. 93tops/w scalable deep learning/inference processor with tetra-parallel Mimd architecture for big-data applications
- Efficient Machine Learning for Big Data: A Review
- Big Data Analytic: Cases for Communications Systems Modeling and Renewable Energy Forecast

## Big Data

- Large-scale Deep Belief Nets with MapReduce
- Project Adam: Building an Efficient and Scalable Deep Learning Training System
- Traffic Flow Prediction With Big Data: A Deep Learning Approach
- Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]
- Tensor index for large scale image retrieval
- Parallel deep neural network training for big data on blue gene/Q
- An Adaptive Approach of Tamil Character Recognition Using Deep Learning with Big Data-A Survey
- Practice in Synonym Extraction at Large Scale
- Application and Architecture of Power Dispatching & Distribution System Using Big Data Technology
- Convolutional Data: Towards Deep Audio Learning from Big Data
- Random Bits Regression: a Strong General Predictor for Big Data
- Deep learning of fMRI big data: a novel approach to subject-transfer decoding
- Computing brains: neuroscience, machine intelligence and big data in the cognitive classroom
- Masterarbeit: Big Data and Machine Learning: A Case Study with Bump Boost
- Promises and Challenges of Big Data Computing in Health Sciences
- Deep learning applications and challenges in big data analytics
- Efficient Machine Learning for Big Data: A Review
- Big Data Analytic: Cases for Communications Systems Modeling and Renewable Energy Forecast

## Big-Data

## Bing Challenge

## Bioinformatics

- Deep learning of the tissue-regulated splicing code
- Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction
- Understanding Protein Dynamics with L1-Regularized Reversible Hidden Markov Models
- Towards the Quantum Machine: Using Scalable Machine Learning Methods to Predict Photovoltaic Efficacy of Organic Molecules
- Multi-task Neural Networks for QSAR Predictions
- SSpro/ACCpro 5: Almost Perfect Prediction of Protein Secondary Structure and Relative Solvent Accessibility Using Profiles, Machine Learning, and Structural Similarity.
- Predicting backbone CÎ± angles and dihedrals from protein sequences by stacked sparse autoâ€encoder deep neural network
- Polypharmacology Modelling Using Proteochemometrics (pcm): Recent Methodological Developments, Applications to Target Families, and Future Prospects
- A generative model of identifying informative proteins from dynamic Ppi networks
- Dann: a deep learning approach for annotating the pathogenicity of genetic variants
- Parallel deep neural network training for big data on blue gene/Q
- Automated computation of arbor densities: a step toward identifying neuronal cell types
- Improved contact predictions using the recognition of protein like contact patterns.
- Automated Gene Expression Pattern Annotation In The Mouse Brain
- Bimmer: a novel algorithm for detecting differential Dna methylation regions from MBDCap-seq data
- Possible computational filter to detect proteins associated to influenza A subtype H1n1.
- Hybrid Ensemble Classification of Tree Genera Using Airborne LiDAR Data
- Deep Belief Networks and Biomedical Text Categorisation
- lncRNA-MFDL: Identification of human long non-coding RNAs by fusing multiple features and using deep learning
- Comparative Study Of Machine Learning Techniques For Supervised Classification Of Biomedical Data
- An Innovative Svm for Wheat Seed Quality Estimationâ‹†

## Biologically

## Biology

- Image-Based Analysis to Study Plant Infection with Human Pathogens
- What We Can Learn From the Primate’s Visual System

## Bird

## Blstm

## Boosted

## Boosting

## Bootstrapping

## Brain

- Deep learning based imaging data completion for improved brain disease diagnosis
- Feature Learning from Incomplete Eeg with Denoising Autoencoder
- Automated Gene Expression Pattern Annotation In The Mouse Brain
- Deep Extreme Learning Machine and Its Application in Eeg Classification
- Brain Ct Image Classification with Deep Neural Networks
- Toward a Universal Cortical Algorithm: Examining Hierarchical Temporal Memory in Light of Frontal Cortical Function
- Hardware-Amenable Structural Learning for Spike-based Pattern Classification using a Simple Model of Active Dendrites
- Nuclei/Cell Detection in Microscopic Skeletal Muscle Fiber Images and Histopathological Brain Tumor Images Using Sparse Optimizations
- Learning Deep Temporal Representations for Brain Decoding
- Brain Edge Detection
- Methodology and Techniques for Building Modular Brain-Computer Interfaces
- Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation
- Pain: a distributed brain information network?
- A spectrum of sharing: maximization of information content for brain imaging data
- Brain as an Emergent Finite Automaton: A Theory and Three Theorems
- Computing brains: neuroscience, machine intelligence and big data in the cognitive classroom
- Neuraledugaming: A Mathematical â€œBrainâ€ to Make Digital Edugames Smart
- A Ultra-Low-Energy Convolution Engine for Fast Brain-Inspired Vision in Multicore Clusters

## Brain Waves

- Does the beat go on?: identifying rhythms from brain waves recorded after their auditory presentation
- Classifying EEG recordings of rhythm perception
- Machines Learning-Towards a New Synthetic Autobiographical Memory
- Deep Learning for the Connectome

## Caffe

## Calibration

## Cancer

- A proteomic signature predicts response to a therapeutic vaccine in pancreas cancer; analysis from the Gi-4000-02 trial
- Integrative Data Analysis of Multi-platform Cancer Data with a Multimodal Deep Learning Approach
- Nuclei/Cell Detection in Microscopic Skeletal Muscle Fiber Images and Histopathological Brain Tumor Images Using Sparse Optimizations
- Cancerous Cell Detection Using Histopathological Image Analysis
- Color Correction Arrangements For Dermoscopy
- Methods And Arrangements For Identifying Dermatological Diagnoses With Clinically Negligible Probabilties
- Automatic melanoma detection in dermatological images

## Car Detection

## Cartography

## Cascade

## Cell

- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Equity-Minded Learning Environments: Pla as a Portal to Fostering Inclusive Excellence

## Challenges

- Big Data Deep Learning: Challenges and Perspectives
- Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]
- Neural-Symbolic Learning and Reasoning: Contributions and Challenges
- The quality and reputation of open, distance and e-learning: what are the challenges?
- Promises and Challenges of Big Data Computing in Health Sciences
- Deep learning applications and challenges in big data analytics

## Character Recognition

- A Study of Designing Compact Classifiers using Deep Neural Networks for Online Handwritten Chinese Character Recognition
- Recognition of Handwritten Characters in Chinese Legal Amounts by Stacked Autoencoders
- An Adaptive Approach of Tamil Character Recognition Using Deep Learning with Big Data-A Survey
- Robust Multi-Layer Hierarchical Model for Digit Character Recognition
- On the Performance Improvement of Devanagri Handwritten Character Recognition
- Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition

## Chinese

## Classification

- DEFEATnet–A Deep Conventional Image Representation for Image Classification
- Applying skip-gram word estimation and SVM-based classification for opinion mining Vietnamese food places text reviews
- Gender classification of subjects from cerebral blood flow changes using Deep Learning
- Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
- P300 classification using deep belief nets
- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- An Improved Bilinear Deep Belief Network Algorithm for Image Classification
- Deep Convolutional Neural Networks for Hyperspectral Image Classification
- Constrained Extreme Learning Machines: A Study on Classification Cases
- Urban Land Use and Land Cover Classification Using Remotely Sensed Sar Data through Deep Belief Networks
- Dynamic texture and scene classification by transferring deep image features
- DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
- Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks
- Image Classification Using Generative Neuro Evolution for Deep Learning
- Imaging and representation learning of solar radio spectrums for classification
- Representation Learning with Deep Extreme Learning Machines for Efficient Image Set Classification
- Deep learning for speech classification and speaker recognition
- Study on Binary Multilayer Neural Networks with Ebp Algorithm on Image Classification
- Be at Odds? Deep and Hierarchical Neural Networks for Classification and Regression of Conflict in Speech
- Image classification using boosted local features with random orientation and location selection
- A novel pLSA based Traffic Signs Classification System
- Iterative 3d shape classification by online metric learning

## Click-Through

## Cloud

- A survey of research on cloud robotics and automation
- Bring Your Own Learner: A Cloud-Based, Data-Parallel Commons for Machine Learning
- Event Pattern Discovery on Ids Traces of Cloud Services
- Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers
- Hive Collective Intelligence for Cloud Robotics: A Hybrid Distributed Robotic Controller Design for Learning and Adaptation

## Clustered

## Clustering

- Ghent University-iMinds at MediaEval 2014 Diverse Images: Adaptive Clustering with Deep Features
- Deep Embedding Network for Clustering
- A Convex Formulation for Spectral Shrunk Clustering
- Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
- Improving relation descriptor extraction with word embeddings and cluster features
- SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering
- Soft context clustering for F0 modeling in HMM-based speech synthesis
- Deep Learning with Nonparametric Clustering
- Deep Learning with Nonparametric Clustering
- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition
- Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features
- FaceNet: A Unified Embedding for Face Recognition and Clustering

## Cnn

- Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation
- Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks

## Coding Scheme

## Cognition

- Biologically Inspired Visual Model With Preliminary Cognition and Active Attention Adjustment
- Deep Image: Scaling up Image Recognition
- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression
- Neural Implementation of Probabilistic Models of Cognition
- Implementation of Dnn-hmm Acoustic Models for Phoneme Recognition
- Sign language recognition using convolutional neural networks
- Robust face recognition via transfer learning for robot partner
- Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition
- On the Performance Improvement of Devanagri Handwritten Character Recognition
- HFirst: A Temporal Approach to Object Recognition
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Hierarchical Recognition System for Target Recognition from Sparse Representations
- Naive-Deep Face Recognition: Touching the Limit of Lfw Benchmark or Not?
- Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
- Optimized multi-channel deep neural network with 2d graphical representation of acoustic speech features for emotion recognition
- Scene Recognition by Manifold Regularized Deep Learning Architecture
- The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid
- Noisy Training for Deep Neural Networks in Speech Recognition
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Deep Multimodal Learning for Audio-Visual Speech Recognition
- DeepID3: Face Recognition with Very Deep Neural Networks
- Freehand Sketch Recognition Using Deep Features
- Deep Neural Networks for Sketch Recognition
- Face frontalization for Alignment and Recognition
- Vehicle Logo Recognition System Based on Convolutional Neural Networks With a Pretraining Strategy
- Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks
- Human Interaction Recognition Using Independent Subspace Analysis Algorithm
- A Hmax with Llc for visual recognition
- A Fast Learning Method for the Multi-layer Perceptron in Automatic Speech Recognition Systems
- Multi-label Learning with Missing Labels for Image Annotation and Facial Action Unit Recognition
- Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
- Robust Excitation-based Features For Automatic Speech Recognition
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Heterogeneous Multi-column ConvNets with a Fusion Framework for Object Recognition
- Machine Learning in Automatic Speech Recognition: A Survey
- DigiRec Proposal: Handwritten Digit Recognition in Hardware
- A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks
- The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition
- Text recognition using deep Blstm networks
- Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition
- Face Recognition Based on Deep Learning
- EmoNets: Multimodal deep learning approaches for emotion recognition in video
- Learning Compact Binary Face Descriptor for Face Recognition
- Learning Shared, Discriminative, and Compact Representations for Visual Recognition
- Facial Expression Recognition via Deep Learning
- Domain Adaptation for Visual Recognition
- Subset based deep learning for Rgb-d object recognition
- Deep learning for speech classification and speaker recognition
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Speech emotion recognition with unsupervised feature learning
- A Minimal Architecture for General Cognition
- 18.1 A 2.71 nJ/pixel 3D-stacked gaze-activated object-recognition system for low-power mobile Hmd applications
- Scene Text Detection and Recognition: Recent Advances and Future Trends

## Cognitive

- Potential of Cognitive Computing and Cognitive Systems
- Computing brains: neuroscience, machine intelligence and big data in the cognitive classroom
- Analysis of Different Sparsity Methods in Constrained Rbm for Sparse Representation in Cognitive Robotic Perception

## Collaborative Filtering

- Implicitly Learning a User Interest Profile for Personalization of Web Search Using Collaborative Filtering
- A Distributional Representation Model For Collaborative Filtering

## Combinatorical Optimization

## Compression

## Computer Vision

- Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines
- Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
- Sparse Deep Belief Net Model for Visual Area {V2}
- An Overview of Color Name Applications in Computer Vision
- Deep learning of representations and its application to computer vision

## Concept Learning

## Consistency

## Constrained

- Spatially Constrained Sparse Coding Scheme for Natural Scene Categorization
- Constrained Extreme Learning Machines: A Study on Classification Cases
- Inter-Tile Reuse Optimization Applied to Bandwidth Constrained Embedded Accelerators
- Analysis of Different Sparsity Methods in Constrained Rbm for Sparse Representation in Cognitive Robotic Perception

## Constructive Neural Networks

## Content-Based

## Contour Detection

## Controller

- Unsupervised neural controller for Reinforcement Learning action-selection: Learning to represent knowledge
- Hive Collective Intelligence for Cloud Robotics: A Hybrid Distributed Robotic Controller Design for Learning and Adaptation

## Convex

## Convex Optimization

## Convexity

## Convnet

## Convnets

## Convoluational Neural Network

## Convolutional

- An Evolutionary Approximation to Contrastive Divergence in Convolutional Restricted Boltzmann Machines
- Sign language recognition using convolutional neural networks
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Robust Tracking via Convolutional Networks without Learning
- Deep Convolutional Neural Networks for Hyperspectral Image Classification
- Deep Convolutional Neural Networks for Object Extraction from High Spatial Resolution Remotely Sensed Imagery
- End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
- A Data-Reuse Aware Accelerator for Large-Scale Convolutional Networks
- Pedestrian Detection Via Pca Filters Based Convolutional Channel
- Aircraft Detection by Deep Convolutional Neural Networks
- Vehicle Logo Recognition System Based on Convolutional Neural Networks With a Pretraining Strategy
- Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Detectionn guided deconvolutional network for hierarchical feature learning
- Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
- Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- Convolutional Fusion Network for Face Verification in the Wild
- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
- Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Deep Clustered Convolutional Kernels
- Deep Convolutional Inverse Graphics Network
- A theoretical argument for complex-valued convolutional networks
- Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos
- 3d Convolutional Neural Networks for Landing Zone Detection from LiDAR
- Deep convolutional networks for pancreas segmentation in Ct imaging
- Conditional generative adversarial nets for convolutional face generation
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection draft version, Cvpr2015

## Convolutional Network

- A new 2.5 D representation for lymph node detection using random sets of deep convolutional neural network observations
- Learning a deep convolutional network for image super-resolution
- Improving multiview face detection with multi-task deep convolutional neural networks
- Detection of Sclerotic Spine Metastases via Random Aggregation of Deep Convolutional Neural Network Classifications
- DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Evolving deep unsupervised convolutional networks for vision-based reinforcement learning
- Reducing structure of deep Convolutional Neural Networks for Huawei Accurate and Fast Mobile Video Annotation Challenge
- Distributed Asynchronous Optimization of Convolutional Neural Networks
- Handwritten Hangul recognition using deep convolutional neural networks
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- Learning Deep and Wide: A Spectral Method for Learning Deep Networks
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Deep Epitomic Convolutional Neural Networks
- Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction
- Large-scale video classification with convolutional neural networks
- Deep convolutional neural networks for sentiment analysis of short texts
- A Winner-Take-All Method for Training Sparse Convolutional Autoencoders
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
- Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning
- Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition
- CNN: Single-label to Multi-label
- Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics
- Action Recognition Using Ensemble of Deep Convolutional Neural Networks
- Discriminative Convolutional Sum-Product Networks on GPU
- Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection
- A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval
- Towards Real-Time Image Understanding with Convolutional Networks
- One weird trick for parallelizing convolutional neural networks
- ImageNet Classification with Deep Convolutional Neural Networks
- Real-time continuous pose recovery of human hands using convolutional networks
- Vehicle License Plate Recognition With Random Convolutional Networks
- SimNets: A Generalization of Convolutional Networks
- Learning Sparse Feature Representations for Music Annotation and Retrievals
- Unsupervised Feature Learning for Audio Classification using Convolutional Deep Belief Networks
- Unsupervised learning of hierarchical representations with convolutional deep belief networks
- Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations
- Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition
- Learning hierarchical representations for face verification with convolutional deep belief networks
- Look Closely: Learning Exemplar Patches for Recognizing Textiles from Product Images
- Cross Dataset Person Re-identification
- Recod at MediaEval 2014: Violent Scenes Detection Task
- Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification
- Early Hierarchical Contexts Learned by Convolutional Networks for Image Segmentation
- Deep Multimodal Fusion: Combining Discrete Events and Continuous Signals
- A new algorithm on variable-rate convolutional broadcast for network coding in cyclic networks
- A Study on Layer Connection Strategies in Stacked Convolutional Deep Belief Networks
- Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns
- Efficient Object Localization Using Convolutional Networks
- Long-term Recurrent Convolutional Networks for Visual Recognition and Description
- Fully Convolutional Networks for Semantic Segmentation
- Deep Deconvolutional Networks for Scene Parsing
- Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection
- Age Estimation by Multi-scale Convolutional Network
- Memory Bounded Deep Convolutional Networks
- Real-time object recognition and orientation estimation using an event-based camera and Cnn
- Occlusion Edge Detection in Rgb-d Frames using Deep Convolutional Networks
- Image Super-Resolution Using Deep Convolutional Networks
- Robust Tracking via Convolutional Networks without Learning
- A Data-Reuse Aware Accelerator for Large-Scale Convolutional Networks
- Detectionn guided deconvolutional network for hierarchical feature learning
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- A theoretical argument for complex-valued convolutional networks
- Deep convolutional networks for pancreas segmentation in Ct imaging

## Convolutional Networks

- Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
- A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis
- Persistent Evidence of Local Image Properties in Generic ConvNets
- Unsupervised feature learning on monaural Doa estimation using convolutional deep belief networks

## Convolutional Neural Network

- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
- Handwritten Hangul recognition using deep convolutional neural networks
- Modelling â€šVisualising and Summarising Documents with a Single Convolutional Neural Network
- Distributed Asynchronous Optimization of Convolutional Neural Networks
- An Efficient Implementation of Deep Convolutional Neural Networks on a Mobile Coprocessor
- Weighted Convolutional Neural Network Ensemble
- Deep convolutional neural networks for large-scale speech tasks
- Deformable Part Models are Convolutional Neural Networks
- Weakly Supervised Object Segmentation with 004 dwaeConvolutional Neural Networks
- Going Deeper with Convolutions
- Tbcnn: A Tree-Based Convolutional Neural Network for Programming Language Processing
- 3d object retrieval with stacked local convolutional autoencoder
- A convolutional neural network approach for face verification
- Spatially-sparse convolutional neural networks
- Deep Convolutional Neural Networks With An Application Towards Geospatial Object Recognition
- Convolutional Neural Network and Convex Optimization
- Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
- Raw Speech Signal-based Continuous Speech Recognition using Convolutional Neural Networks
- Music Genre Classification Using Convolutional Neural Network
- Vehicle Type Classification Using Unsupervised Convolutional Neural Network
- Cascaded Convolutional Neural Network for Eye Detection Under Complex Scenarios
- Vehicle Type Classification Using Semi-Supervised Convolutional Neural Network
- Deep Convolutional Neural Network for Image Deconvolution
- DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks
- Food Detection and Recognition Using Convolutional Neural Network
- Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification
- Fully Convolutional Neural Networks for Crowd Segmentation
- Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
- Visual Sentiment Prediction with Deep Convolutional Neural Networks
- Learning to Generate Chairs with Convolutional Neural Networks
- The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
- Scene Recognition Using Mid-level features from Cnn
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
- Convolutional Neural Networks at Constrained Time Cost
- Image Recognition Using Convolutional Neural Networks
- Reading Text in the Wild with Convolutional Neural Networks
- Real-Time Grasp Detection Using Convolutional Neural Networks
- Teaching Deep Convolutional Neural Networks to Play Go
- Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
- DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
- Learning Block Group Sparse Representation Combined with Convolutional Neural Networks for Rgb-d Object Recognition
- Bayesian Deep Deconvolutional Learning
- Flattened Convolutional Neural Networks for Feedforward Acceleration
- Move Evaluation In Go Using Deep Convolutional Neural Networks
- Robotic Grasping System Using Convolutional Neural Networks
- Fully Convolutional Multi-Class Multiple Instance Learning
- Striving for Simplicity: The All Convolutional Net
- Learning Compact Convolutional Neural Networks with Nested Dropout
- Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures
- Learning linearly separable features for speech recognition using convolutional neural networks
- Generative Modeling of Convolutional Neural Networks
- Spectral classification using convolutional neural networks
- Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation
- Sign language recognition using convolutional neural networks
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Deep Convolutional Neural Networks for Hyperspectral Image Classification
- Deep Convolutional Neural Networks for Object Extraction from High Spatial Resolution Remotely Sensed Imagery
- Aircraft Detection by Deep Convolutional Neural Networks
- Vehicle Logo Recognition System Based on Convolutional Neural Networks With a Pretraining Strategy
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
- Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks
- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
- Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos
- 3d Convolutional Neural Networks for Landing Zone Detection from LiDAR
- Rotation-invariant convolutional neural networks for galaxy morphology prediction

## Convolutional Neural Networks

- Memory Access Optimized Scheduling Scheme for DCNNs on a Mobile Processor
- Combining the Best of Graphical Models and ConvNets for Semantic Segmentation
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

## Corpora

- Applying deep learning techniques on medical corpora from the World Wide Web: a prototypical system and evaluation
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism
- On Using Monolingual Corpora in Neural Machine Translation

## Cortical Processing

## Ct

- Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression
- An Evolutionary Approximation to Contrastive Divergence in Convolutional Restricted Boltzmann Machines
- Stochastic Spectral Descent for Restricted Boltzmann Machines
- Explicit knowledge extraction in information-theoretic supervised multi-layered Som
- Gender classification of subjects from cerebral blood flow changes using Deep Learning
- Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
- Unsupervised dictionary extraction of bird vocalizations and new tools on assessing and visualizing bird activity
- Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition
- On the Performance Improvement of Devanagri Handwritten Character Recognition
- HFirst: A Temporal Approach to Object Recognition
- Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Accurate localized short term weather prediction for renewables planning
- Utilizing Deep Learning for Content-based Community Detection
- Unsupervised neural controller for Reinforcement Learning action-selection: Learning to represent knowledge
- Transductive Multi-view Zero-Shot Learning
- Shape Feature Encoding via Fisher Vector for Efficient Fall Detection in Depth-Videos
- Improving Pedestrian Detection with Selective Gradient Self-Similarity Feature
- Video summarization based on Subclass Support Vector Data Description
- Retrieval Term Prediction Using Deep Belief Networks
- Scene Recognition by Manifold Regularized Deep Learning Architecture
- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- Neural Networks Based Methods for Voice Activity Detection in a Multi-room Domestic Environment
- Unidirectional Long Short-term Memory Recurrent Neural Network With Recurrent Output Layer For Low-latency Speech â€¦
- An Effective Solution to Double Counting Problem in Human Pose Estimation
- Deep Convolutional Neural Networks for Hyperspectral Image Classification
- Where am I? Predicting Montreal Neighbourhoods from Google Street View Images
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Deep Convolutional Neural Networks for Object Extraction from High Spatial Resolution Remotely Sensed Imagery
- Filtered Channel Features for Pedestrian Detection
- Deep Twin Support Vector Machine
- Pedestrian Detection Via Pca Filters Based Convolutional Channel
- A spectrum of sharing: maximization of information content for brain imaging data
- Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
- The Improvement of Structured-output Regression Forests on Detection about Face Partsâ‹†
- Interactions Between Gaussian Processes and Bayesian Estimation
- Aircraft Detection by Deep Convolutional Neural Networks
- Exploring Latent Structure in Data: Algorithms and Implementations
- Deep learning of fMRI big data: a novel approach to subject-transfer decoding
- Advanced Mean Field Theory of Restricted Boltzmann Machine
- Hybrid Orthogonal Projection and Estimation (hope): A New Framework to Probe and Learn Neural Networks
- Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
- Monte Carlo Integration Using Spatial Structure of Markov Random Field
- Deep Representations for Iris, Face, and Fingerprint Spoofing Detection
- Exploration of Deep Belief Networks for Vowel-like regions detection
- Method and System for Predicting Spatial and Temporal Distributions of Therapeutic Substance Carriers
- Electronic Imaging & Signal Processing Automatic quality prediction of authentically distorted pictures
- Continuous Hyper-parameter Learning for Support Vector Machines
- Human Interaction Recognition Using Independent Subspace Analysis Algorithm
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Adaptive Road Detection via Context-aware Label Transfer
- Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters
- Recognizing Multi-view Objects with Occlusions using a Deep Architecture
- Detectionn guided deconvolutional network for hierarchical feature learning
- DeepSense: A novel learning mechanism for traffic prediction with taxi Gps traces
- Fast Neural Networks with Circulant Projections
- Predictive Analytics of Sensor Data Using Distributed Machine Learning Techniques
- Multi-label Learning with Missing Labels for Image Annotation and Facial Action Unit Recognition
- ‘Hiring a Nashville sensation': using narrative learning to develop the problem solving skills of contract law students
- Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data
- Inferring 3d Object Pose in Rgb-d Images
- Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
- Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships
- Conditional Restricted Boltzmann Machines for Multi-label Learning with Incomplete Labels
- Towards Building Deep Networks with Bayesian Factor Graphs
- Abstract Learning via Demodulation in a Deep Neural Network
- Deep Transform: Error Correction via Probabilistic Re-Synthesis
- segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
- Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
- Principles of Explanatory Debugging to Personalize Interactive Machine Learning
- Universal Memory Architectures for Autonomous Machines
- Rectified Factor Networks
- Artificial intelligence: Learning to see and act
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Heterogeneous Multi-column ConvNets with a Fusion Framework for Object Recognition
- Detecting spammers on social Networks
- Forecasting And Inventory Performance In Direct-store Delivery Supply Chain: Case Of Retailer In Serbia
- A Dictionary Approach to Ebsd Indexing
- Fuzzy Restricted Boltzmann Machine and Its Fast Learning Algorithm
- Overcoming Intractability in Unsupervised Learning (Invited Talk)}}”, author = “S Arora, EW Mayr, N Ollinger
- The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition
- Deep Learning Framework with Confused Sub-Set Resolution Architecture for Automatic Arabic Diacritization
- Learning Semantic Hierarchies: A Continuous Vector Space Approach
- When Are Tree Structures Necessary for Deep Learning of Representations?
- Cascade object detection with complementary features and algorithms
- Automated Construction of Visual-Linguistic Knowledge via Concept Learning from Cartoon Videos
- Two-Stage Learning to Predict Human Eye Fixations via SDAEs
- Why Does Unsupervised Deep Learning WORK?-Aperspective From Group Theory
- To Skip or not to Skip? A Dataset of Spontaneous Affective Response of Online Advertising (sara) for Audience Behavior Analysis
- Predicting the Quality of User-Generated Answers Using Co-Training in Community-based Question Answering Portals
- Imaging and representation learning of solar radio spectrums for classification
- Robust people counting using sparse representation and random projection
- Beyond Lowest-Warping Cost Action Selection in Trajectory Transfer
- Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features
- Unsupervised word sense induction using rival penalized competitive learning
- Deep Human Parsing with Active Template Regression
- Learning Compact Binary Face Descriptor for Face Recognition
- Learning Shared, Discriminative, and Compact Representations for Visual Recognition
- Hive Collective Intelligence for Cloud Robotics: A Hybrid Distributed Robotic Controller Design for Learning and Adaptation
- Deep Reinforcement Learning for constructing meaning by ‘babbling’
- Subset based deep learning for Rgb-d object recognition
- Awareness, Integration and Interconnectedness Contemplative Practices of Higher Education Professionals
- Mask selective regularization for restricted Boltzmann machines
- Deep Structured Semantic Model Produced Using Click-Through Data
- Knowledge Representation for Image Feature Extraction
- Single image super-resolution by approximated Heaviside functions
- Automatic melanoma detection in dermatological images
- Replicating the Research of the Paper:â€œApplication of Artificial Neural Network in Detection of Probing Attacksâ€
- Predicting Entry-Level Categories
- Predicting Pinterest: Automating a distributed human computation
- Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images
- Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine
- A Minimal Architecture for General Cognition
- Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis
- Feature maps driven no-reference image quality prediction of authentically distorted images
- Be at Odds? Deep and Hierarchical Neural Networks for Classification and Regression of Conflict in Speech
- Image classification using boosted local features with random orientation and location selection
- Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory
- An Online-Traffic-Prediction Based Route Finding Mechanism for Smart City
- Scene Text Detection and Recognition: Recent Advances and Future Trends
- 3d Convolutional Neural Networks for Landing Zone Detection from LiDAR
- Implementation of a Practical Distributed Calculation System with Browsers and JavaScript, and Application to Distributed Deep Learning
- Deep convolutional networks for pancreas segmentation in Ct imaging
- Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis
- Modelling User Affect and Sentiment in Intelligent User Interfaces: A Tutorial Overview
- Learning Hypergraph-regularized Attribute Predictors
- Predicting ocean health, one plankton at a time
- Optimizing Neural Networks with Kronecker-factored Approximate Curvature
- A Hierarchical Neuro-Fuzzy Architecture for Human Behavior Analysis
- Detection of Alzheimer’s disease using group lasso SVM-based region selection
- Vehicle Detection in Aerial Imagery: A small target detection benchmark
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection draft version, Cvpr2015
- On Invariance and Selectivity in Representation Learning
- Rank Subspace Learning for Compact Hash Codes
- Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder
- I Can Has Cheezburger? A Nonparanormal Approach to Combining Textual and Visual Information for Predicting and Generating Popular Meme Descriptions

## Data Center

## Data Mining

## Data-Parallel

## Dataset

- Large-Scale Deep Learning on the Yfcc100m Dataset
- To Skip or not to Skip? A Dataset of Spontaneous Affective Response of Online Advertising (sara) for Audience Behavior Analysis

## Dcnn

## Decision Making

## Decision Tree

## Deep Belief Nets

## Deep Belief Network

- Towards adaptive learning with improved convergence of deep belief networks on graphics processing units
- Deep Belief Networks used on High Resolution Multichannel Electroencephalography Data for Seizure Detection
- Using Deep Belief Networks for Vector-Based Speaker Recognition
- Statistical Parametric Speech Synthesis using Weighted Multi-distribution Deep Belief Network
- Deep Belief Networks (DBNs)
- Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition
- Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning
- Large-scale Deep Belief Nets with MapReduce
- Camera-based Sudoku recognition with Deep Belief Network
- Prediction of Stock Trend Based on Deep Belief Networks
- Deep Tempering
- Accuracy evaluation of deep belief networks with fixed-point arithmetic
- Deep Adaptive Networks for Visual Data Classification
- Learning Local Receptive Fields in Deep Belief Networks for Visual Feature Detection
- Deep learning-based target customer position extraction on social network
- Deep belief network based Crf for spoken language understanding
- A Study on Layer Connection Strategies in Stacked Convolutional Deep Belief Networks
- Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2d and 3d Images
- Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy
- Systems and methods for analyzing data using deep belief networks (dbn) and identifying a pattern in a graph
- Deep Belief Networks and Biomedical Text Categorisation
- Unsupervised feature learning on monaural Doa estimation using convolutional deep belief networks
- A Study of Deep Belief Network Based Chinese Speech Emotion Recognition
- Auditory Scene Classification with Deep Belief Network
- Retrieval Term Prediction Using Deep Belief Networks
- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- An Improved Bilinear Deep Belief Network Algorithm for Image Classification
- Urban Land Use and Land Cover Classification Using Remotely Sensed Sar Data through Deep Belief Networks
- Exploration of Deep Belief Networks for Vowel-like regions detection
- F0 Modeling In Hmm-Based Speech Synthesis System Using Deep Belief Network
- Speech Separation based on Deep Belief Network
- Learning Document Semantic Representation with Hybrid Deep Belief Network

## Deep Boltzmann Machines

## Deep Convex Networks

## Deep Learning

## Deep Neural Network

- Predicting backbone CÎ± angles and dihedrals from protein sequences by stacked sparse autoâ€encoder deep neural network
- Recognition Of Acoustic Events Using Deep Neural Networks
- Audio Concept Classification With Hierarchical Deep Neural Networks
- Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training
- Classification of Artistic Styles using Binarized Features Derived from a Deep Neural Network
- Deep neural network based load forecast
- Parallel batch pattern training algorithm for deep neural network
- Distributed Data Mining Based on Deep Neural Network for Wireless Sensor Network
- Qr Code Localization Using Deep Neural Networks
- Irrelevant Variability Normalization via Hierarchical Deep Neural Networks for Online Handwritten Chinese Character Recognition
- A Real-time Hand Posture Recognition System Using Deep Neural Networks
- A Deep Neural Network Approach to Automatic Birdsong Recognition
- Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks
- Deep Neural Networks For Spoken Dialog Systems
- Parallel deep neural network training for big data on blue gene/Q
- A Study of Designing Compact Classifiers using Deep Neural Networks for Online Handwritten Chinese Character Recognition
- Acoustic emotion recognition using deep neural network
- Research on deep neural network’s hidden layers in phoneme recognition
- Cross-language transfer learning for deep neural network based speech enhancement
- Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent
- Multiple time-span feature fusion for deep neural network modeling
- Investigation of stochastic Hessian-Free optimization in Deep neural networks for speech recognition
- TANDEM-bottleneck feature combination using hierarchical Deep Neural Networks
- Random feedback weights support learning in deep neural networks
- How transferable are features in deep neural networks?
- Deep Neural Network Based Speech Separation for Robust Speech Recognition
- An Optimization of Deep Neural Networks in Asr using Singular Value Decomposition
- Speech Separation of A Target Speaker Based on Deep Neural Networks
- Real-time Head Orientation from a Monocular Camera using Deep Neural Network
- Deep Neural Networks
- Brain Ct Image Classification with Deep Neural Networks
- Feature Representation Learning in Deep Neural Networks
- Representation Sharing and Transfer in Deep Neural Networks
- Deep Neural Network-Hidden Markov Model Hybrid Systems
- Improving Deep Neural Networks Using State Projection Vectors Of Subspace Gaussian Mixture Model As Features
- A Survey of Regularization Methods for Deep Neural Network
- Environmentally robust Asr front-end for deep neural network acoustic models
- Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
- Object Recognition Using Deep Neural Networks: A Survey
- Supplementary Material: On the Number of Linear Regions of Deep Neural Networks
- No-reference image quality assessment with shearlet transform and deep neural Networks
- Deep neural network adaptation for children’s and adults’ speech recognition
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Fixed-point feedforward deep neural network design using weights+ 1, 0, andâˆ’ 1
- Learning Activation Functions to Improve Deep Neural Networks
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- Multi-modal Sensor Registration for Vehicle Perception via Deep Neural Networks
- An analysis of deep neural networks for texture classification
- Improved Mispronunciation Detection with Deep Neural Network Trained Acoustic Models and Transfer Learning based Logistic Regression Classifiers
- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Sound Retrieval From Vocal Imitation Queries Based On Deep Neural Networks
- Keystroke Dynamics Advances for Mobile Devices Using Deep Neural Network
- Noisy Training for Deep Neural Networks in Speech Recognition
- DeepID3: Face Recognition with Very Deep Neural Networks
- Deep Neural Networks for Sketch Recognition
- Over-Sampling in a Deep Neural Network
- Abstract Learning via Demodulation in a Deep Neural Network
- Application of Deep Neural Network in Estimation of the Weld Bead Parameters
- segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
- Scalable Bayesian Optimization Using Deep Neural Networks
- Sequence transcription with deep neural networks
- Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
- Improving acoustic model for English Asr System using deep neural network
- Deep Neural Networks for Acoustic Modeling
- Data driven articulatory synthesis with deep neural networks

## Deep Sigmoid Belief Networks

## Deeply-Supervised Nets

## Deformation

## Deformations

## Demodulation

## Denoising

- Training Stacked Denoising Autoencoders for Representation Learning
- Convergence of gradient based pre-training in Denoising autoencoders
- Denoising Autoencoders for fast Combinatorial Black Box Optimization
- Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder

## Depression

## Depth Estimation

## Depth-Videos

## Dermatology

## Devops

## Diabetes

## Diabetic

## Diacritization

## Dictionary

- Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning
- Unsupervised dictionary extraction of bird vocalizations and new tools on assessing and visualizing bird activity
- A Dictionary Approach to Ebsd Indexing

## Dictionary Extraction

## Digit Classification

## Digit Recognition

## Disambiguation

## Discriminative

- DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification
- Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
- DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking
- Learning Shared, Discriminative, and Compact Representations for Visual Recognition
- Learning Discriminative Feature Representations for Visual Categorization

## Discriminative Learning

## Disease

- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Pd Disease State Assessment in Naturalistic Environments using Deep Learning
- Detection of Alzheimer’s disease using group lasso SVM-based region selection

## Disjunctive

## Distance Functions

## Distributed

- Predictive Analytics of Sensor Data Using Distributed Machine Learning Techniques
- Singa: A Distributed System for Deep Learning
- Predicting Pinterest: Automating a distributed human computation
- Implementation of a Practical Distributed Calculation System with Browsers and JavaScript, and Application to Distributed Deep Learning

## Distributed System

## Dnn

- Implementation of Dnn-hmm Acoustic Models for Phoneme Recognition
- Indexing Images for Visual Memory by Using Dnn Descriptorsâ€“Preliminary Experiments

## Domain Invariance

## Domain-Adversarial

## Drone

## Dropout

- Temporal Dropout of Changes Approach to Convolutional Learning of Spatio-Temporal Features
- On the Inductive Bias of Dropout
- Learning Compact Convolutional Neural Networks with Nested Dropout
- Efficient batchwise dropout training using submatrices

## Drug

## Drug Target Detection

## Economy

## Edge Detection

## Education

- Contexto: lessons learned from mobile context inference
- Predicting Academic Achievement of High-School Students Using Machine Learning

## Eeg

- Classifying EEG recordings of rhythm perception
- Feature Learning from Incomplete Eeg with Denoising Autoencoder
- Deep Extreme Learning Machine and Its Application in Eeg Classification
- Learning Deep Temporal Representations for Brain Decoding
- Methodology and Techniques for Building Modular Brain-Computer Interfaces

## Electricity

## Electricity Forecast

## Embedded

## Emotion

- Deep Learning for Emotional Speech Recognition
- Prosodic, spectral and voice quality feature selection using a long-term stopping criterion for audio-based emotion recognition
- Acoustic emotion recognition using deep neural network
- Improving generation performance of speech emotion recognition by denoising autoencoders
- Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video
- Speech Emotion Recognition Using Cnn
- Emotion Modeling and Machine Learning in Affective Computing
- Emotion Recognition in the Wild with Feature Fusion and Multiple Kernel Learning
- A Study of Deep Belief Network Based Chinese Speech Emotion Recognition
- The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid
- EmoNets: Multimodal deep learning approaches for emotion recognition in video
- Speech emotion recognition with unsupervised feature learning

## Emotion Detection

## Encoding

- Two-layer contractive encodings for learning stable nonlinear features
- Predictive Encoding of Contextual Relationships for Perceptual Inference, Interpolation and Prediction

## Encryption

## Energy

- Quantum Energy Regression using Scattering Transforms
- Efficient Generation of Energy and Performance Pareto Front for Fpga Designs
- A Ultra-Low-Energy Convolution Engine for Fast Brain-Inspired Vision in Multicore Clusters
- Big Data Analytic: Cases for Communications Systems Modeling and Renewable Energy Forecast

## Energy Efficiency

## Energy Efficient

- M2C: Energy efficient mobile cloud system for deep learning
- Energy efficient neural networks for big data analytics
- Brain-inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform
- Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition
- Stt-snn: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks

## Ensemble Learning

- Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
- Soft sensor development for nonlinear and timeâ€varying processes based on supervised ensemble learning with improved process state partition

## Entities

## Entity

## Error Correction

- Deep Transform: Error Correction via Probabilistic Re-Synthesis
- Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis

## Estimation

- Nice: Non-linear Independent Components Estimation
- Applying skip-gram word estimation and SVM-based classification for opinion mining Vietnamese food places text reviews
- An Effective Solution to Double Counting Problem in Human Pose Estimation
- Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
- Interactions Between Gaussian Processes and Bayesian Estimation
- Hybrid Orthogonal Projection and Estimation (hope): A New Framework to Probe and Learn Neural Networks
- Hands Deep in Deep Learning for Hand Pose Estimation
- Using Distance Estimation and Deep Learning to Simplify Calibration in Food Calorie Measurement
- Made: Masked Autoencoder for Distribution Estimation
- Application of Deep Neural Network in Estimation of the Weld Bead Parameters
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Deeply-Learned Feature for Age Estimation
- Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

## Evaluation

- Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns
- CIDEr: Consensus-based Image Description Evaluation
- Preliminary evaluation of hyperopt algorithms on HPOLib
- Software Quality Evaluation of Face Recognition APIs & Libraries

## Event

- Event Pattern Discovery on Ids Traces of Cloud Services
- Spike Event Based Learning in Neural Networks

## Event Detection

- Video Event Detection via Multi-modality Deep Learning
- Audio-Concept Features and Hidden Markov Models for Multimedia Event Detection

## Examination

## Experimental

## Extreme Learning

## Eye Detection

- Eye gaze for spoken language understanding in multi-modal conversational interactions
- Smartphone based visible iris recognition using deep sparse filtering
- Cascaded Convolutional Neural Network for Eye Detection Under Complex Scenarios

## Eye Tracking

## Face

- Robust face recognition via transfer learning for robot partner
- Naive-Deep Face Recognition: Touching the Limit of Lfw Benchmark or Not?
- The Improvement of Structured-output Regression Forests on Detection about Face Partsâ‹†
- DeepID3: Face Recognition with Very Deep Neural Networks
- Face frontalization for Alignment and Recognition
- Deep Representations for Iris, Face, and Fingerprint Spoofing Detection
- Dense 3d Face Alignment from 2d Videos in Real-Time
- Convolutional Fusion Network for Face Verification in the Wild
- Supervised descent method with low rank and sparsity constraints for robust face alignment
- Face Recognition Based on Deep Learning
- Learning Compact Binary Face Descriptor for Face Recognition
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Logistic Similarity Metric Learning For Face Verification
- Modelling User Affect and Sentiment in Intelligent User Interfaces: A Tutorial Overview
- Conditional generative adversarial nets for convolutional face generation

## Face Detection

- Improving multiview face detection with multi-task deep convolutional neural networks
- Learning to encode motion using spatio-temporal synchrony
- Detecting People in Cubist Art
- Deep Metric Learning for Person Re-Identification
- Cross Dataset Person Re-identification

## Face Expression Analysis

## Face Recognition

- Deep learning for real-time robust facial expression recognition on a smartphone
- Deep learning multi-view representation for face recognition
- Deep learning face representation by joint identification-verification
- Learning and Transferring Multi-task Deep Representation for Face Alignment
- Facial Landmark Detection by Deep Multi-task Learning
- Shared Representation Learning for Heterogeneous Face Recognition
- Web-Scale Training for Face Identification
- Emotion Detection using Deep Belief Networks
- Hough Networks for Head Pose Estimation and Facial Feature Localization
- Human Action Recognition Using Deep Probabilistic Graphical Models
- Recurrent Models of Visual Attention
- Deep learning: Modeling high-level face features through deep networks
- Recognition of Facial Attributes using Adaptive Sparse Representations of Random Patches
- Hough Networks for Head Pose Estimation and Facial Feature Localization
- A Neural Autoregressive Approach to Attention-based Recognition
- Recognition of Facial Expression via Kernel Pca Network
- Deep Regression for Face Alignment
- A convolutional neural network approach for face verification
- Facial Landmark Localization using Hierarchical Pose Regression
- Hsr: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection
- A Deep Graph Embedding Network Model for Face Recognition
- Learning Multiscale Active Facial Patches for Expression Analysis
- Fast Localization of Facial Landmark Points
- The relation of eye gaze and face pose: Potential impact on speech recognition
- Low rank driven robust facial landmark regression
- Deep Representations for Iris, Face, and Fingerprint Spoofing Attack Detection
- Facial Feature Point Detection: A Comprehensive Survey
- Learning Invariant Color Features for Person Re-Identification
- Extended Supervised Descent Method for Robust Face Alignment
- Facial Expression Analysis Based on High Dimensional Binary Features
- DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification
- Discriminative Deep Face Shape Model for Facial Point Detection
- Learning Compact Face Representation: Packing a Face into an int32
- Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations
- Set-label modeling and deep metric learning on person re-identification
- Automatic face annotation in Tv series by video/script alignment
- Real-time Head Orientation from a Monocular Camera using Deep Neural Network
- Topic-aware Deep Auto-encoders (tda) for Face Alignment
- Deep Learning Face Attributes in the Wild
- Effective Face Frontalization in Unconstrained Images
- Learning Face Representation from Scratch
- Deeply learned face representations are sparse, selective, and robust
- Shared features for multiple face-based biometrics
- A twice face recognition algorithm
- Feature Selection And Extraction For Babyface Recognition
- Personalized Face Image Retrieval Based On Gmkl
- Software Quality Evaluation of Face Recognition APIs & Libraries
- Online Smart Face Morphing Engine with Prior Constraints and Local Geometry Preservation
- A Learning Framework for Age Rank Estimation based on Face Images with Scattering Transform
- Privileged Information-based Conditional Structured Output Regression Forest for Facial Point Detection
- Robust face recognition via transfer learning for robot partner
- Naive-Deep Face Recognition: Touching the Limit of Lfw Benchmark or Not?
- DeepID3: Face Recognition with Very Deep Neural Networks
- Face Recognition Based on Deep Learning
- Learning Compact Binary Face Descriptor for Face Recognition
- FaceNet: A Unified Embedding for Face Recognition and Clustering

## Facial

- Multi-label Learning with Missing Labels for Image Annotation and Facial Action Unit Recognition
- Learning facial expressions from an image
- Facial Expression Recognition via Deep Learning
- Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine

## Factorization

- SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering
- Neural Network Regularization via Robust Weight Factorization

## Fault Diagnosis

## Feature

- Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression
- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions
- Learning features and their transformations from natural videos
- Transferring Rich Feature Hierarchies for Robust Visual Tracking
- Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
- Shape Feature Encoding via Fisher Vector for Efficient Fall Detection in Depth-Videos
- Improving Pedestrian Detection with Selective Gradient Self-Similarity Feature
- Filtered Channel Features for Pedestrian Detection
- Freehand Sketch Recognition Using Deep Features
- Dynamic texture and scene classification by transferring deep image features
- DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification
- Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters
- Detectionn guided deconvolutional network for hierarchical feature learning
- Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
- Dynamic Feature-Adaptive Subdivision
- Fingerprint Image Enhancement Using Unsupervised Hierarchical Feature Learning
- Robust Excitation-based Features For Automatic Speech Recognition
- Deeply-Learned Feature for Age Estimation
- Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
- The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition
- Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers
- Cascade object detection with complementary features and algorithms
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism
- DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking
- On the Problem of Features Variability in Sequence Learning Problems
- Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features
- Fitting 3d Morphable Models using Local Features
- Knowledge Representation for Image Feature Extraction
- Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images
- Speech emotion recognition with unsupervised feature learning
- Learning Discriminative Feature Representations for Visual Categorization
- Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis
- Feature maps driven no-reference image quality prediction of authentically distorted images
- Image classification using boosted local features with random orientation and location selection
- DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection draft version, Cvpr2015

## Feature Discovery

## Feature Encoding

## Feature Extraction

- Hierarchical spatiotemporal feature extraction using recurrent online clustering
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Deep learning of feature representation with multiple instance learning for medical image analysis
- A review of unsupervised feature learning and deep learning for time-series modeling
- Challenge Huawei challenge: Fusing multimodal features with deep neural networks for Mobile Video Annotation
- Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks
- Learning Rich Features from RGB-D Images for Object Detection and Segmentation
- Improved Music Feature Learning with Deep Neural Networks
- Feature Selection and Learning for Semantic Segmentation
- Audio-only bird classification using unsupervised feature learning
- Hsr: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection
- Feature Selection Based on Dependency Margin
- Improving Acoustic Model for Vietnamese Large Vocabulary Continuous Speech Recognition System Using Deep Bottleneck Features
- Local deep feature learning framework for 3d shape
- Learning Sparse Feature Representations for Music Annotation and Retrievals
- Unsupervised Feature Learning for Audio Classification using Convolutional Deep Belief Networks
- Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition
- Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines
- Learning and Selecting Features Jointly with Point-wise Gated {Boltzmann} Machines
- An exact mapping between the Variational Renormalization Group and Deep Learning
- Meta-parameter free unsupervised sparse feature learning
- High-Order Semi-RBMs and Deep Gated Neural Networks for Feature Interaction Identification and Non-Linear Semantic Indexing
- Unsupervised Feature Learning For Bootleg Detection Using Deep Learning Architectures
- Learning Local Receptive Fields in Deep Belief Networks for Visual Feature Detection
- Recod at MediaEval 2014: Violent Scenes Detection Task
- A Method For Extracting Information From The Web Using Deep Learning Algorithm
- Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array
- Learning Multiple Complex Features Based on Classification Results
- Multiple time-span feature fusion for deep neural network modeling
- Pre-release sales forecasting: A model-driven context feature extraction approach
- Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection
- Da-ccd: A novel action representation by deep architecture of local depth feature
- Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
- Wind Power Prediction and Pattern Feature Based on Deep Learning Method
- Geodesic Invariant Feature (gif): A Local Descriptor in Depth
- Prototype-Based Discriminative Feature Learning for Kinship Verification
- Visual Causal Feature Learning
- Matrix and Tensor Features for Discriminative Learning
- Integrating Stroke-distribution Information Into Spatial Feature Extraction For Automatic Handwriting Recognition
- Feature Weight Tuning for Recursive Neural Networks
- Score Function Features for Discriminative Learning: Matrix and Tensor Framework
- Sparse, guided feature connections in an Abstract Deep Network
- Exploiting high level feature for dynamic textures recognition
- Learning Feature Representations with a Cost-Relevant Sparse Autoencoder
- Feature Selection And Extraction For Babyface Recognition
- Learning linearly separable features for speech recognition using convolutional neural networks
- C-SVDDNet: An Effective Single-Layer Network for Unsupervised Feature Learning
- View-independent object detection using shared local features
- lncRNA-MFDL: Identification of human long non-coding RNAs by fusing multiple features and using deep learning
- Unsupervised Feature Learning for Dense Correspondences across Scenes
- Knowledge Representation for Image Feature Extraction

## Feature Recognition

## Feature Representation

- Feature Representation Learning in Deep Neural Networks
- Sharing Model With Multi-level Feature Representations

## Feature Selection

## Feature Tuning

## Features

- Learning features and their transformations from natural videos
- Filtered Channel Features for Pedestrian Detection
- Freehand Sketch Recognition Using Deep Features
- Dynamic texture and scene classification by transferring deep image features
- Robust Excitation-based Features For Automatic Speech Recognition
- Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers
- Cascade object detection with complementary features and algorithms
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism
- On the Problem of Features Variability in Sequence Learning Problems
- Fitting 3d Morphable Models using Local Features
- Image classification using boosted local features with random orientation and location selection

## Filtering

## Finance

- Neural Networks for Runtime Verification
- Gpu Implementation of a Deep Learning Network for Financial Prediction

## Fine Tuning

## Fine-Tuning

## Fingerprint Detection

## Fingerprint Recognition

- Fingerprint Classification Based on Depth Neural Network
- Deep Representations for Iris, Face, and Fingerprint Spoofing Attack Detection

## Fisher Vectors

## Fmri

## Font Recognition

## Food Detection

## Fpga

- Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
- Efficient Generation of Energy and Performance Pareto Front for Fpga Designs

## Fpga-Based

## Framework

- Purine: A bi-graph based deep learning framework
- A Learning Framework for Age Rank Estimation based on Face Images with Scattering Transform
- Hybrid Orthogonal Projection and Estimation (hope): A New Framework to Probe and Learn Neural Networks
- Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework
- Emeuro: a framework for generating multi-purpose accelerators via deep learning
- Heterogeneous Multi-column ConvNets with a Fusion Framework for Object Recognition
- A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks
- Deep Learning Framework with Confused Sub-Set Resolution Architecture for Automatic Arabic Diacritization
- apsis-Framework for Automated Optimization of Machine Learning Hyper Parameters

## Freehand

## Frequency Domain

## Fuzzy Learning

## Galaxy

## Game

## Games

- Replicating the Paper â€œPlaying Atari with Deep Reinforcement Learningâ€[MKS
- Camera-based Sudoku recognition with Deep Belief Network
- Learning with serious games: is fun playing the game a predictor of learning success?
- Teaching Deep Convolutional Neural Networks to Play Go
- Move Evaluation In Go Using Deep Convolutional Neural Networks
- Neuraledugaming: A Mathematical â€œBrainâ€ to Make Digital Edugames Smart

## Gaussian

- Improving Deep Neural Networks Using State Projection Vectors Of Subspace Gaussian Mixture Model As Features
- Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
- Interactions Between Gaussian Processes and Bayesian Estimation

## Generative

- Generative Adversarial Nets
- Image Classification Using Generative Neuro Evolution for Deep Learning
- GSNs: Generative Stochastic Networks
- Conditional generative adversarial nets for convolutional face generation

## Generative Deep Learning

## Genetic Programming

## Gesture

## Gesture Recognition

- Deep Dynamic Neural Networks for Gesture Segmentation and Recognition
- Static hand gesture recognition using stacked Denoising Sparse Autoencoders
- A Study of Feature Combination in Gesture Recognition with Kinect
- Feature learning based on Sae-pca network for Human gesture recognition in Rgbd images
- A hierarchical structure for gesture recognition using Rgb-d sensor
- ModDrop: adaptive multi-modal gesture recognition

## Go

- Teaching Deep Convolutional Neural Networks to Play Go
- Move Evaluation In Go Using Deep Convolutional Neural Networks

## Googlenet

## Gpu

- A fast deep learning system using GPU
- GPU Accelerated Computation and Real-time Rendering of Cellular Automata Model for Spatial Simulation
- Towards adaptive learning with improved convergence of deep belief networks on graphics processing units
- GPUs: High-performance Accelerators for Parallel Applications: The multicore transformation (Ubiquity symposium)
- Large scale recurrent neural network on GPU
- Detection of retransmissions in 10G Ethernet using GPUs
- More Faster Self-Organizing Maps by General Purpose on Graphics Processing Units
- Fast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks
- Discriminative Convolutional Sum-Product Networks on GPU
- Determining the difficulty of accelerating problems on a Gpu
- Optimising Purely Functional Gpu Programs (Thesis)
- Gpu Implementation of a Deep Learning Network for Financial Prediction
- cuDNN: Efficient Primitives for Deep Learning
- Introducing CURRENNTâ€“the Munich open-source Cuda RecurREnt Neural Network Toolkit
- Gaussian Process Models with Parallelization and Gpu acceleration
- Query Optimization in Heterogeneous Cpu/gpu Environment for Time Series Databases
- A GPGPU-Based Acceleration of Fault-Tolerant Mlp Learnings
- Theano-based Large-Scale Visual Recognition with Multiple GPUs
- A Gpu Implementation of GoogLeNet

## Gradient

- Accelerated gradient temporal difference learning algorithms
- Improving Pedestrian Detection with Selective Gradient Self-Similarity Feature
- Gradient-based Hyperparameter Optimization through Reversible Learning
- Convergence of gradient based pre-training in Denoising autoencoders

## Gradient-Based

## Graph

- Graph-Based Supervised Automatic Target Detection
- Systems and methods for analyzing data using deep belief networks (dbn) and identifying a pattern in a graph

## Graphical Model

## Graphics

## Graphs

## Grasping System

## Hadoop

## Hand Pose

## Handwriting Recognition

- Icfhr2014 Competition on Handwritten Text Recognition on tranScriptorium Datasets (HTRtS)
- Writer Adaptation using Bottleneck Features and Discriminative Linear Regression for Online Handwritten Chinese Character Recognition
- Deep-Belief-Network based Rescoring for Handwritten Word Recognition
- Irrelevant Variability Normalization via Hierarchical Deep Neural Networks for Online Handwritten Chinese Character Recognition
- A Tibetan Component Representation Learning Method for Online Handwritten Tibetan Character Recognition
- Managing Real-time Handwriting Recognition
- Real-time Stroke-order And Stroke-direction Independent Handwriting Recognition
- Multi-script Handwriting Recognition Using A Universal Recognizer

## Handwritten

- On the Performance Improvement of Devanagri Handwritten Character Recognition
- DigiRec Proposal: Handwritten Digit Recognition in Hardware

## Handwritten Recognition

## Hardware

- An Analog VLSI Deep Machine Learning Implementation
- Adaptive Many-Core Machines
- Motivation and Preliminaries
- Training itself: Mixed-signal training acceleration for memristor-based neural network.
- A Fully Pipelined FPGA Architecture of a Factored Restricted Boltzmann Machine Artificial Neural Network
- Performance Prediction by Deep Learning Methods for Semiconductor Manufacturing
- Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics
- Hardware-Amenable Structural Learning for Spike-based Pattern Classification using a Simple Model of Active Dendrites
- A Biological-Realtime Neuromorphic System in 28 nm Cmos using Low-Leakage Switched Capacitor Circuits
- Scalable Hardware Efficient Deep Spatio-Temporal Inference Networks
- DigiRec Proposal: Handwritten Digit Recognition in Hardware

## Hash

- DeepHash: Getting Regularization, Depth and Fine-Tuning Right
- Deep learning with application to hashing
- Two Dimensional Hashing for Visual Tracking
- Shoe: Supervised Hashing with Output Embeddings
- Rank Subspace Learning for Compact Hash Codes

## Hashing

- Inductive Transfer Deep Hashing for Image Retrieval
- Cross-Media Hashing with Neural Networks
- Deep learning with application to hashing
- Two Dimensional Hashing for Visual Tracking
- Shoe: Supervised Hashing with Output Embeddings

## Healthcare

- Deep learning based imaging data completion for improved brain disease diagnosis
- A new 2.5 D representation for lymph node detection using random sets of deep convolutional neural network observations
- Detection of Sclerotic Spine Metastases via Random Aggregation of Deep Convolutional Neural Network Classifications
- Deep Belief Networks used on High Resolution Multichannel Electroencephalography Data for Seizure Detection
- Comparing Raw Data and Feature Extraction for Seizure Detection with Deep Learning Methods
- ML-o-scope: a diagnostic visualization system for deep machine learning pipelines
- Pruning Deep Neural Networks by Optimal Brain Damage
- DEEP LEARNING VIA STACKED SPARSE AUTOENCODERS FOR AUTOMATED VOXEL-WISE BRAIN PARCELLATION BASED ON FUNCTIONAL CONNECTIVITY (Thesis format: Monograph)
- Deep Learning for the Connectome
- Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection
- Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks

## Hearing Aid

## Heart Failure

## Helicopter

## Hessian

## Hierarchical

- Hierarchical Recognition System for Target Recognition from Sparse Representations
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Detectionn guided deconvolutional network for hierarchical feature learning
- Fingerprint Image Enhancement Using Unsupervised Hierarchical Feature Learning
- Deep Hierarchical Parsing for Semantic Segmentation
- Hierarchical learning of grids of microtopics
- Be at Odds? Deep and Hierarchical Neural Networks for Classification and Regression of Conflict in Speech
- A Hierarchical Neuro-Fuzzy Architecture for Human Behavior Analysis

## High-Dimensional Data

## Hmax

## Hmm

- Deep Neural Network-Hidden Markov Model Hybrid Systems
- Hidden Markov Models and the Variants
- A deep Hmm model for multiple keywords spotting in handwritten documents
- Soft context clustering for F0 modeling in HMM-based speech synthesis
- Audio-Concept Features and Hidden Markov Models for Multimedia Event Detection

## Hmm-Based

## Hough Transform

## Human Behavior

- Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data
- A Hierarchical Neuro-Fuzzy Architecture for Human Behavior Analysis

## Human Pose

## Human-Level

- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Human-level control through deep reinforcement learning

## Hyperspectral

- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- Deep Convolutional Neural Networks for Hyperspectral Image Classification

## Image Classification

- Combining Newton interpolation and deep learning for image classification
- DEFEATnet–A Deep Conventional Image Representation for Image Classification
- An Improved Bilinear Deep Belief Network Algorithm for Image Classification
- Deep Convolutional Neural Networks for Hyperspectral Image Classification
- Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
- Image Classification Using Generative Neuro Evolution for Deep Learning
- Study on Binary Multilayer Neural Networks with Ebp Algorithm on Image Classification
- Image classification using boosted local features with random orientation and location selection

## Image De-Noising

## Image Parsing

## Image Quality

## Image Recognition

- Deep learning based imaging data completion for improved brain disease diagnosis
- A Deep Learning Pipeline for Image Understanding and Acoustic Modeling
- Learning a deep convolutional network for image super-resolution
- Cross-media relevance mining for evaluating text-based image search engine
- A deep learning approach to the classification of 3D CAD models
- Signature identification via efficient feature selection and GPU-based SVM classifier
- Handwritten Hangul recognition using deep convolutional neural networks
- ML-o-scope: a diagnostic visualization system for deep machine learning pipelines
- Deep Network Cascade for Image Super-resolution
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- Learning Rich Features from RGB-D Images for Object Detection and Segmentation
- Generic Object Detection With Dense Neural Patterns and Regionlets
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition
- $ N\^{} 4$-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
- Single Image Super-resolution Reconstruction with Neural Network and Gaussian Process Regression
- Handwritten digit recognition using sparse deep architectures
- 3D ShapeNets for 2.5 D object recognition and Next-Best-View prediction
- Mining knowledge from clicks: MSR-Bing image retrieval challenge
- Fast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks
- A DEEP LEARNING APPROACH TO DOCUMENT IMAGE QUALITY ASSESSMENT
- Structured Prediction for Object Detection in Deep Neural Networks
- Multi-modal Feature Fusion for 3D Shape Recognition and Retrieval
- 3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- FEATURE GENERATION FOR QUANTIFICATION OF VISUAL SIMILARITY
- Mental Rotation by Optimizing Transforming Distance
- Effective Multi-Modal Retrieval based on Stacked Auto-Encoders
- Hierarchical kernel-based rotation and scale invariant similarity
- Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images
- Quantifying the Energy Efficiency of Object Recognition and Optical Flow
- Deep learning for image classification
- Local Feature Design Concepts, Classification, and Learning
- Object Detection and Viewpoint Estimation with Auto-masking Neural Network
- Large-Scale Scene Classification Using Gist Feature
- What you need to know about the state-of-the-art computational models of object-vision: A tour through the models
- Learning Sparse FRAME Models for Natural Image Patterns
- Surpassing Human-Level Face Verification Performance on LFW with GaussianFace
- Object recognition with hierarchical discriminant saliency networks
- Towards Real-Time Image Understanding with Convolutional Networks
- ImageNet Classification with Deep Convolutional Neural Networks
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
- Handwritten Hangul recognition using deep convolutional neural networks
- Joint Road Network Extraction From A Set Of High Resolution Satellite Images
- Self-taught Object Localization with Deep Networks
- Ibm research australia at lifeclef2014: Plant identification task
- MindLab at ImageCLEF 2014: Scalable Concept Image Annotation
- Sabanci-okan system at lifeclef 2014 plant identification competition
- Image classification via learning dissimilarity measure in non-euclidean spaces
- Compute Less to Get More: Using Orc to Improve Sparse Filtering
- Weakly Supervised Object Segmentation with 004 dwaeConvolutional Neural Networks
- Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning
- Mlia at ImageCLFE 2014 Scalable Concept Image Annotation Challenge
- Random Cascaded-Regression Copse for Robust Facial Landmark Detection
- Contour Motion Estimation for Asynchronous Event-Driven Cameras
- Difference representation learning using stacked restricted Boltzmann machines for change detection in Sar images
- Object Classification via PCANet and Color Constancy Model
- The Application of Sift Image Matching in the Information Query Based on Mpi Acceleration
- Defect Detecting Technology Based on Machine Vision of Industrial Parts
- Neural Networks and Neuroscience-Inspired Computer Vision
- Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification
- 1-hkust: Object Detection in Ilsvrc 2014
- Domain Adaptive Neural Networks for Object Recognition
- Image Classification with A Deep Network Model based on Compressive Sensing
- Do More Dropouts in Pool5 Feature Maps for Better Object Detection
- Continuous gesture recognition from articulated poses
- Image-Based Analysis to Study Plant Infection with Human Pathogens
- Free-Form Region Description with Second-Order Pooling
- MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
- Hyper-Spectral Image Analysis with Partially-Latent Regression and Spatial Markov Dependencies
- Classifying Gray-scale Sar Images: Adeep Learning Approach
- Qr Code Localization Using Deep Neural Networks
- Localization of Visual Codes in the Dct Domain Using Deep Rectifier Neural Networks
- Deep Convolutional Neural Networks With An Application Towards Geospatial Object Recognition
- Vehicle License Plate Recognition With Random Convolutional Networks
- Human gesture recognition using three-dimensional integral imaging
- Saliency-guided deep framework for image quality assessment
- Helping robots see the big picture
- Exploiting the deep learning paradigm for recognizing human actions
- Deep Model for Classification of Hyperspectral image using Restricted Boltzmann Machine
- HAck: A system for the recognition of human actions by kernels of visual strings
- Explain Images with Multimodal Recurrent Neural Networks
- Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning
- Semantics of Visual Discrimination
- Multi-View Semi-Supervised Learning Based Image Annotation
- Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
- Tensor index for large scale image retrieval
- Indirect shape analysis for 3d shape retrieval
- Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
- A Simple Stochastic Algorithm for Structural Features Learning
- Deep supervised, but not unsupervised, models may explain It cortical representation
- Fully automatic segmentation of ultrasound common carotid artery images based on machine learning
- Automatic vertebrae localization, identification, and segmentation using deep learning and statistical models
- Deep Adaptive Networks for Visual Data Classification
- Coarse-to-Fine Minimization of Some Common Nonconvexities
- Multiple Spatio-Temporal Scales Neural Network for Contextual Visual Recognition of Human Actions
- Ghent University-iMinds at MediaEval 2014 Diverse Images: Adaptive Clustering with Deep Features
- Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding
- Nonlinear Supervised Locality Preserving Projections for Visual Pattern Discrimination
- Supervised feature learning via â„“2-norm regularized logistic regression for 3d object recognition
- Adaptive learning in a compartmental model of visual cortex-how feedback enables stable category learning and refinement
- Semi-Supervised Learning for Rgb-d Object Recognition
- Efficient image representation for object recognition via pivots selection
- Regularized Hierarchical Feature Learning with Non-Negative Sparsity and Selectivity for Image Classification
- Learning deep dynamical models from image pixels
- DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification
- Towards a Visual Turing Challenge
- Semantic parsing for priming object detection in indoors Rgb-d scenes
- Combining heterogenous features for 3d hand-held object recognition
- Rapid: Rating Pictorial Aesthetics using Deep Learning
- Fused one-vs-all mid-level features for fine-grained visual categorization
- DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks
- Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge
- Inductive Transfer Deep Hashing for Image Retrieval
- Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification
- Handwritten Digits Classification
- MatchBox: Indoor Image Matching via Box-like Scene Estimation
- Understanding image representations by measuring their equivariance and equivalence
- Hypercolumns for Object Segmentation and Fine-grained Localization
- The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
- A deep Hmm model for multiple keywords spotting in handwritten documents
- Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
- Visual Scene Representations: Sufficiency, Minimality, Invariance and Approximations
- Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a Uav
- Image Recognition Using Convolutional Neural Networks
- Image Super-Resolution Using Deep Convolutional Networks
- Bikers are like tobacco shops, formal dressers are like suits: Recognizing Urban Tribes with Caffe
- Deep Image: Scaling up Image Recognition

## Image Recognitionx

## Image Representation

## Image Segmentation

- Early Hierarchical Contexts Learned by Convolutional Networks for Image Segmentation
- Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation

## Imagery

- Vehicle Detection in Aerial Imagery: A small target detection benchmark

## Imaging

- Machine learning for transient discovery in Pan-STARRS1 difference imaging
- A spectrum of sharing: maximization of information content for brain imaging data
- Electronic Imaging & Signal Processing Automatic quality prediction of authentically distorted pictures
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Imaging and representation learning of solar radio spectrums for classification
- Deep convolutional networks for pancreas segmentation in Ct imaging

## Improvisation

## Indexing

## Induction

## Inductive Bias

- Inductive Bias for Semi-supervised Extreme Learning Machine
- On the Inductive Bias of Dropout
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

## Information

## Information Retrieval

- RankCNN: When learning to rank encounters the pseudo preference feedback
- Effective Multi-Modal Retrieval based on Stacked Auto-Encoders
- A compositional hierarchical model for music information retrieval
- Deep Sentence Embedding Using the Long Short Term Memory Network: Analysis and Application to Information Retrieval

## Information Theory

## Information-Theoretic

## Infrastructure

## Interpolation

## Invariant

- Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle
- Rotation-invariant convolutional neural networks for galaxy morphology prediction

## Javascript

## Kernel

- Training Generalized Feedforword Kernelized Neural Networks on Very Large Datasets for Regression Using Minimal-Enclosing-Ball Approximation
- On optimizing machine learning workloads via kernel fusion
- Hypothesis Testing with Kernel Embeddings on Big and Interdependent Data
- Deep Clustered Convolutional Kernels
- Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels

## Kernel Methods

- Kernel methods match deep neural networks on timit
- How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets

## Kernels

- Riemannian Coding and Dictionary Learning: Kernels to the Rescue
- Deep Clustered Convolutional Kernels
- Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels

## Kickback

## Labeling

## Lasso

## Latent Structure

## Lattice

## Learning To Rank

## Lecun

- Efficient Object Localization Using Convolutional Networks
- Unsupervised Learning of Spatiotemporally Coherent Metrics
- Deep learning with Elastic Averaging Sgd

## Lfw

## Linear Model

## Linear Models

## Log-Likelihood

## Logistic

## Long Short-Term Memory

## Low Resolution

## Lstm

- Text recognition using deep Blstm networks
- Compositional Distributional Semantics with Long Short Term Memory

## Machine Translation

- Sequence to Sequence Learning with Neural Networks
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Neural Machine Translation by Jointly Learning to Align and Translate
- AN AUTOENCODER WITH BILINGUAL SPARSE FEATURES FOR IMPROVED STATISTICAL MACHINE TRANSLATION
- Deep Learning for Natural Language Processing and Machine Translation
- Non-linear Learning for Statistical Machine Translation
- On Using Monolingual Corpora in Neural Machine Translation

## Mahout

## Mammogram Analysis

## Manufacturing

## Matrix

## Max Pooling

## Medical

- Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
- Applying deep learning techniques on medical corpora from the World Wide Web: a prototypical system and evaluation

## Medical Records

## Medicine

- Deep learning of feature representation with multiple instance learning for medical image analysis
- Detection of Sclerotic Spine Metastases via Random Aggregation of Deep Convolutional Neural Network Classifications
- Deep Belief Networks used on High Resolution Multichannel Electroencephalography Data for Seizure Detection
- Comparing Raw Data and Feature Extraction for Seizure Detection with Deep Learning Methods
- ML-o-scope: a diagnostic visualization system for deep machine learning pipelines
- Pruning Deep Neural Networks by Optimal Brain Damage
- DEEP LEARNING VIA STACKED SPARSE AUTOENCODERS FOR AUTOMATED VOXEL-WISE BRAIN PARCELLATION BASED ON FUNCTIONAL CONNECTIVITY (Thesis format: Monograph)
- Deep Learning for the Connectome
- Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection
- Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks
- Polypharmacology Modelling Using Proteochemometrics (pcm): Recent Methodological Developments, Applications to Target Families, and Future Prospects
- A proteomic signature predicts response to a therapeutic vaccine in pancreas cancer; analysis from the Gi-4000-02 trial
- Fully automatic segmentation of ultrasound common carotid artery images based on machine learning
- Automatic vertebrae localization, identification, and segmentation using deep learning and statistical models
- Testing AutoTrace: A machine-learning approach to automated tongue contour data extraction
- Automatic Vaginal Bacteria Segmentation and Classification Based on Superpixel and Deep Learning
- Predicting Likelihood of Hospitalization with Subset-Filtered Emerging Patterns
- Deep Structured learning for mass segmentation from Mammograms
- Clinical Decision Analysis using Decision Tree
- High-definition 3d Image Processing Technology for Ultrasound Diagnostic Scanners
- Signal Processing in Next-Generation Prosthetics [Special Reports]
- Integrative Data Analysis of Multi-platform Cancer Data with a Multimodal Deep Learning Approach
- Machine Learning for Medical Applications
- Adapting Linguistic Tools for the Analysis of Italian Medical Records
- Nuclei/Cell Detection in Microscopic Skeletal Muscle Fiber Images and Histopathological Brain Tumor Images Using Sparse Optimizations
- Learning Deep Temporal Representations for Brain Decoding
- Cancerous Cell Detection Using Histopathological Image Analysis
- Dermoscopic Data Acquisition Employing Display Illumination
- Gesture-based Dermatologic Data Collection And Presentation
- Color Correction Arrangements For Dermoscopy
- Methods And Arrangements For Identifying Dermatological Diagnoses With Clinically Negligible Probabilties
- Gender classification of subjects from cerebral blood flow changes using Deep Learning
- Automatic melanoma detection in dermatological images
- Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder

## Memory

## Memristor

## Metric

## Metric Learning

## Microblog

## Mimd

## Mine Detection

## Missing

## Mobile

- M2C: Energy efficient mobile cloud system for deep learning
- A 240 G-ops/s Mobile Coprocessor for Deep Neural Networks
- Brain-inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform
- An Efficient Implementation of Deep Convolutional Neural Networks on a Mobile Coprocessor
- Memory Access Optimized Scheduling Scheme for DCNNs on a Mobile Processor
- Contexto: lessons learned from mobile context inference
- Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
- Smartphone based visible iris recognition using deep sparse filtering
- Non-parametric Bayesian Learning with Deep Learning Structure and Its Applications in Wireless Networks
- Travel Behavior Characterization Using Raw Accelerometer Data Collected from Smartphones
- Stt-snn: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks
- Can Deep Learning Revolutionize Mobile Sensing?
- Towards an Embodied Developing Vision System
- Keystroke Dynamics Advances for Mobile Devices Using Deep Neural Network

## Monte Carlo

## Motion

- The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid
- Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
- EmoNets: Multimodal deep learning approaches for emotion recognition in video
- Speech emotion recognition with unsupervised feature learning

## Motion Detection

- Learning motion-difference features using Gaussian restricted Boltzmann machines for efficient human action recognition
- Contour Motion Estimation for Asynchronous Event-Driven Cameras

## Motion Recognition

## Mri

- Brain Edge Detection
- Deep learning of fMRI big data: a novel approach to subject-transfer decoding
- Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder

## Multi-Label

- Multi-label Learning with Missing Labels for Image Annotation and Facial Action Unit Recognition
- Conditional Restricted Boltzmann Machines for Multi-label Learning with Incomplete Labels

## Multicore

- Adaptive Many-Core Machines
- Motivation and Preliminaries
- Training Large Scale Deep Neural Networks on the Intel Xeon Phi Many-core Coprocessor
- Machine Learning for Adaptive Many-Core Machines-A Practical Approach
- A Ultra-Low-Energy Convolution Engine for Fast Brain-Inspired Vision in Multicore Clusters

## Multimedia

## Multimodal

- Multimodal Analytics and its Data Ecosystem
- Integrative Data Analysis of Multi-platform Cancer Data with a Multimodal Deep Learning Approach
- Multimodal Transfer Deep Learning for Audio Visual Recognition

## Music

- Chord Recognition with Stacked Denoising Autoencoders
- A compositional hierarchical model for music information retrieval
- Fusing Music and Video Modalities Using Multi-timescale Shared Representations
- Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition
- Machine Learning Applied to Musical Improvisation

## Natural Language Processing

- Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis
- Adaptive recursive neural network for target-dependent twitter sentiment classification
- Modeling interestingness with deep neural networks
- Deep convolutional neural networks for sentiment analysis of short texts
- Learning Character-level Representations for Part-of-Speech Tagging
- Language Modeling with Sum-Product Networks
- Learning Sparse Recurrent Neural Networks in Language Modeling
- Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model
- Think Positive: Towards Twitter Sentiment Analysis from Scratch
- A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words
- Max-Margin Tensor Neural Network for Chinese Word Segmentation
- Query expansion for mixed-script information retrieval
- Query Expansion for Multi-script Information Retrieval
- AN AUTOENCODER WITH BILINGUAL SPARSE FEATURES FOR IMPROVED STATISTICAL MACHINE TRANSLATION
- Learning Distributed Representations of Natural Language Text with Artificial Neural Networks
- Modeling Newswire Events using Neural Networks for Anomaly Detection
- A semantic matching energy function for learning with multi-relational data
- Modelling â€šVisualising and Summarising Documents with a Single Convolutional Neural Network
- Introduction to Word2vec and its application to find predominant word senses
- Rc-net: A General Framework for Incorporating Knowledge into Word Representations
- Analyzing sparse dictionaries for online learning with kernels
- Coupled Projections for Semi-supervised Adaptation of Dictionaries
- Automatic Arabic diacritics restoration based on deep nets
- Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars
- Learning Bilingual Embedding Model for Cross-Language Sentiment Classification
- Fuzzy Subjective Sentiment Phrases: A Context Sensitive and Self-Maintaining Sentiment Lexicon
- Deep Learning for Natural Language Processing and Machine Translation
- Deep Recursive Neural Networks for Compositionality in Language
- Text Mining with the Stanford CoreNLP
- Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
- From Captions to Visual Concepts and Back
- Show and Tell: A Neural Image Caption Generator
- Deep Belief Networks and Biomedical Text Categorisation
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
- Deep Learning for Answer Sentence Selection
- Improving relation descriptor extraction with word embeddings and cluster features
- Practice in Synonym Extraction at Large Scale
- Reading Text in the Wild with Convolutional Neural Networks
- Learning Word Representations from Relational Graphs
- Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning
- An Information Theoretic Approach to Quantifying Text Interestingness
- Adapting Linguistic Tools for the Analysis of Italian Medical Records
- Translating Videos to Natural Language Using Deep Recurrent Neural Networks
- Data collection and language understanding of food descriptions
- Cnu System in Ntcir-11 IMine Task
- Tuta1 at the Ntcir-11 IMine Task
- Deep Learning for Web Search and Natural Language Processing
- Open Domain Question Answering via Semantic Enrichment
- Syntax-based Deep Matching of Short Texts
- Deep Multilingual Correlation for Improved Word Embeddings

## Network

- Detection of retransmissions in 10G Ethernet using GPUs
- Distributed Data Mining Based on Deep Neural Network for Wireless Sensor Network

## Network Analysis

## Network Congestion

## Networking

## Neuromorphic

- SPINDLE: SPINtronic deep learning engine for large-scale neuromorphic computing
- Thermodynamic-RAM Technology Stack
- A neuromorphic categorization system with Online Sequential Extreme Learning
- A Biological-Realtime Neuromorphic System in 28 nm Cmos using Low-Leakage Switched Capacitor Circuits

## Neuron

- Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels

## Neuroscience

## Newton

- Combining Newton interpolation and deep learning for image classification
- Subsampled Hessian Newton Methods for Su-pervised Learning

## Noise

- Analyzing noise in autoencoders and deep networks
- Scheduled denoising autoencoders
- Chord Recognition with Stacked Denoising Autoencoders
- Regularizing Recurrent Networks-On Injected Noise and Norm-based Methods
- Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding
- Training Deep Neural Networks on Noisy Labels with Bootstrapping

## Noiseness

- A Noisy-Or Discriminative Restricted Boltzmann Machine for Recognizing Handwriting Style Development
- Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments
- Feature Learning from Incomplete Eeg with Denoising Autoencoder

## Noisy

## Noisy Data

## Non-Convex

- Online Bandit Learning for a Special Class of Non-convex Losses
- RMSProp and equilibrated adaptive learning rates for non-convex optimization
- On Graduated Optimization for Stochastic Non-Convex Problems

## Non-Euclidian

## Numerical

## Numerics

- Accuracy evaluation of deep belief networks with fixed-point arithmetic
- Low precision arithmetic for deep learning

## Object Classification

## Object Detection

- Unsupervised Learning of Semantics of Object Detections for Scene Categorization
- DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
- Background Prior Based Salient Object Detection via Deep Reconstruction Residual
- View-independent object detection using shared local features

## Object Localization

- Efficient Object Localization Using Convolutional Networks
- Self-Taught Object Localization with Deep Networks

## Object Recognition

- Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition
- Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection
- Analysis of Multilayer Neural Networks for Object Recognition
- Real-time object recognition and orientation estimation using an event-based camera and Cnn
- HFirst: A Temporal Approach to Object Recognition
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Heterogeneous Multi-column ConvNets with a Fusion Framework for Object Recognition
- The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition
- Subset based deep learning for Rgb-d object recognition

## Object Reconstruction

## Occlusion

- Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
- Recognizing Multi-view Objects with Occlusions using a Deep Architecture
- 6 On Handling Occlusions Using Hmax

## Occlusions

- Recognizing Multi-view Objects with Occlusions using a Deep Architecture
- 6 On Handling Occlusions Using Hmax

## Online Learning

- Analyzing sparse dictionaries for online learning with kernels
- Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification

## Open Source

## Optimization

- Query Optimization in Heterogeneous Cpu/gpu Environment for Time Series Databases
- The normalized risk-averting error criterion for avoiding nonglobal local minima in training neural networks
- Efficient Benchmarking of Hyperparameter Optimizers via Surrogates
- Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization
- Convolutional Neural Networks at Constrained Time Cost
- Memory Bounded Deep Convolutional Networks
- Sparse Representations, Numerical Linear Algebra, and Optimization
- Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM
- Inter-Tile Reuse Optimization Applied to Bandwidth Constrained Embedded Accelerators
- Gradient-based Hyperparameter Optimization through Reversible Learning
- RMSProp and equilibrated adaptive learning rates for non-convex optimization
- Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
- Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework
- Scalable Bayesian Optimization Using Deep Neural Networks
- Denoising Autoencoders for fast Combinatorial Black Box Optimization
- apsis-Framework for Automated Optimization of Machine Learning Hyper Parameters
- On Graduated Optimization for Stochastic Non-Convex Problems

## Optimized

- Jointly Optimized Regressors for Image Super-resolution

## Orientation Estimation

## Over-Sampling

## Overview

- Deep Learning in Neural Networks: An Overview
- Draft: Deep Learning in Neural Networks: An Overview
- Big Data Deep Learning: Challenges and Perspectives
- Neural Networks: A Review
- Deep Learning
- An Anarchy of Methods: Current Trends in How Intelligence Is Abstracted in Ai
- An Overview of Deep Generative Models
- An Overview of Color Name Applications in Computer Vision
- Modelling User Affect and Sentiment in Intelligent User Interfaces: A Tutorial Overview

## Pancreas

## Parallel

## Parallelization

- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
- GPUs: High-performance Accelerators for Parallel Applications: The multicore transformation (Ubiquity symposium)
- One weird trick for parallelizing convolutional neural networks
- Parallel batch pattern training algorithm for deep neural network
- The Application of Sift Image Matching in the Information Query Based on Mpi Acceleration
- Gaussian Process Models with Parallelization and Gpu acceleration
- A Ultra-Low-Energy Convolution Engine for Fast Brain-Inspired Vision in Multicore Clusters

## Parameter

- Continuous Hyper-parameter Learning for Support Vector Machines
- Gradient-based Hyperparameter Optimization through Reversible Learning
- Application of Deep Neural Network in Estimation of the Weld Bead Parameters
- apsis-Framework for Automated Optimization of Machine Learning Hyper Parameters

## Parameter Tuning

## Parameters

- Application of Deep Neural Network in Estimation of the Weld Bead Parameters
- apsis-Framework for Automated Optimization of Machine Learning Hyper Parameters

## Parsing

- Deep Human Parsing with Active Template Regression
- Deep Hierarchical Parsing for Semantic Segmentation

## Part-Of-Speech

## Pca

## Pedestrian Detection

- Pedestrian Detection Based on Multi-Stage Unsupervised Learning
- Pedestrian Detection aided by Deep Learning Semantic Tasks
- Pedestrian Detection From Salient Regions
- Improving Pedestrian Detection with Selective Gradient Self-Similarity Feature
- Taking a Deeper Look at Pedestrians
- Filtered Channel Features for Pedestrian Detection
- Pedestrian Detection Via Pca Filters Based Convolutional Channel

## Perception

## Perceptron

## Performance Improvement

- Improving Deep Neural Network Performance by Reusing Features Trained with Transductive Transference
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- Improve Performance in Deep Neural Networks:(1) Cost Functions, and (2) Reusable learning
- Improving Transfer Learning Accuracy by Reusing Stacked Denoising Autoencoders
- Alternate Layer Sparsity and Intermediate Fine-tuning for Deep Autoencoders
- Transfer of Learning Across Deep Networks to Improve Performance in Problems with Few Labelled Data
- Acceleration Strategies for Speech Recognition Based on Deep Neural Networks
- On the Performance Improvement of Devanagri Handwritten Character Recognition

## Personalize

## Phoneme

## Photo Adjustment

## Photonic

## Physics

- Searching for exotic particles in high-energy physics with deep learning
- Deep Learning in High-Energy Physics: Improving the Search for Exotic Particles
- Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning
- Enhanced Higgs Boson to Ï„+ Ï„âˆ’ Search with Deep Learning

## Plankton

## Planning

- Accurate localized short term weather prediction for renewables planning
- Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning

## Platform

- Mariana: Tencent Deep Learning Platform and its Applications
- DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Implementation and evaluation of deep neural networks (DNN) on mainstream heterogeneous systems
- A scalable and topology configurable protocol for distributed parameter synchronization
- Large scale recurrent neural network on GPU
- Distributed Asynchronous Optimization of Convolutional Neural Networks
- Kaldi+ PDNN: Building DNN-based ASR Systems with Kaldi and PDNN
- Improving deep neural networks for LVCSR using dropout and shrinking structure
- Deep Epitomic Convolutional Neural Networks
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
- A brief survey on deep belief networks and introducing a new object oriented MATLAB toolbox (DeeBNet)
- Minerva: A Scalable and Highly Efficient Training Platform for Deep Learning
- Integrative Data Analysis of Multi-platform Cancer Data with a Multimodal Deep Learning Approach

## Pooling

## Pose

- An Effective Solution to Double Counting Problem in Human Pose Estimation
- Hands Deep in Deep Learning for Hand Pose Estimation
- Inferring 3d Object Pose in Rgb-d Images
- Emeuro: a framework for generating multi-purpose accelerators via deep learning
- Learning Descriptors for Object Recognition and 3d Pose Estimation
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

## Pose Recognition

## Posture Recognition

- Deep learning for posture analysis in fall detection
- A Real-time Hand Posture Recognition System Using Deep Neural Networks
- A Biologically Inspired Human Posture Recognition System

## Pre-Training

- Statistical-mechanical analysis of pre-training and fine tuning in deep learning
- Convergence of gradient based pre-training in Denoising autoencoders

## Predicting

- Where am I? Predicting Montreal Neighbourhoods from Google Street View Images
- Method and System for Predicting Spatial and Temporal Distributions of Therapeutic Substance Carriers
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data
- Predicting the Quality of User-Generated Answers Using Co-Training in Community-based Question Answering Portals
- Predicting Entry-Level Categories
- Predicting Pinterest: Automating a distributed human computation
- Predicting ocean health, one plankton at a time
- I Can Has Cheezburger? A Nonparanormal Approach to Combining Textual and Visual Information for Predicting and Generating Popular Meme Descriptions

## Prediction

- Accurate localized short term weather prediction for renewables planning
- Retrieval Term Prediction Using Deep Belief Networks
- Electronic Imaging & Signal Processing Automatic quality prediction of authentically distorted pictures
- DeepSense: A novel learning mechanism for traffic prediction with taxi Gps traces
- Feature maps driven no-reference image quality prediction of authentically distorted images
- Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory
- An Online-Traffic-Prediction Based Route Finding Mechanism for Smart City
- Rotation-invariant convolutional neural networks for galaxy morphology prediction

## Predictive Modelling

## Predictors

## Pretraining

## Probabilistic

## Processor

## Programming Language Processing

## Prosthetics

## Proteinomics

- Possible computational filter to detect proteins associated to influenza A subtype H1n1.
- lncRNA-MFDL: Identification of human long non-coding RNAs by fusing multiple features and using deep learning
- Fast loop modeling for protein structures

## Python

## Quality

- Deep Learning For Objective Quality Assessment Of 3d Images
- Parsing Occluded People by Flexible Compositions
- Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
- No-reference image quality assessment with shearlet transform and deep neural Networks
- On the Stability of Deep Networks
- Software Quality Evaluation of Face Recognition APIs & Libraries
- An Innovative Svm for Wheat Seed Quality Estimationâ‹†

## Quantum

## Quantum Computing

- An introduction to quantum machine learning
- An Algorithm of Quantum Restricted Boltzmann Machine Network Based on Quantum Gates and Its Application
- Quantum Deep Learning
- Simulating a perceptron on a quantum computer
- Majorana Zero Modes and Topological Quantum Computation

## Quantum Deep Learning

## Random Field

- Monte Carlo Integration Using Spatial Structure of Markov Random Field
- Conditional Random Fields as Recurrent Neural Networks

## Random Fields

## Random Forests

- Deep Distributed Random Samplings for Supervised Learning: An Alternative to Random Forests?
- Random Forests Can Hash

## Ranking

- Multiple level visual semantic fusion method for image re-ranking
- Ranking with Recursive Neural Networks and Its Application to Multi-document Summarization

## Rbm

- Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)
- Analysis of Different Sparsity Methods in Constrained Rbm for Sparse Representation in Cognitive Robotic Perception

## Recommendation Systems

## Recommender Systems

- Improving Content-based and Hybrid Music Recommendation using Deep Learning
- Collaborative Deep Learning for Recommender Systems
- Cars2: Learning Context-aware Representations for Context-aware Recommendations
- Deep Exponential Families

## Rectified

## Rectifiers

## Rectifiers:

## Recurrant Neural Networks

- Regularizing Recurrent Networks-On Injected Noise and Norm-based Methods
- Translating Videos to Natural Language Using Deep Recurrent Neural Networks

## Recurrent

- Unidirectional Long Short-term Memory Recurrent Neural Network With Recurrent Output Layer For Low-latency Speech â€¦
- Conditional Random Fields as Recurrent Neural Networks
- Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
- Draw: A Recurrent Neural Network For Image Generation
- A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks
- Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets

## Recurrent Nets

## Recurrent Networks

## Recurrent Neural Networks

## Regression

- A Deep and Stable Extreme Learning Approach for Classification and Regression
- Transparent-supported radiance regression function
- Random Bits Regression: a Strong General Predictor for Big Data
- The Improvement of Structured-output Regression Forests on Detection about Face Partsâ‹†
- Quantum Energy Regression using Scattering Transforms
- Deep Human Parsing with Active Template Regression

## Regularization

- Manifold Regularized Deep Neural Networks
- A comparison of dropout and weight decay for regularizing deep neural networks
- A Survey of Regularization Methods for Deep Neural Network
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
- Neural Network Regularization via Robust Weight Factorization
- DeepHash: Getting Regularization, Depth and Fine-Tuning Right
- Mask selective regularization for restricted Boltzmann machines

## Reinforcement Learning

- Evolving deep unsupervised convolutional networks for vision-based reinforcement learning
- Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning
- Hierarchical reinforcement learning in a biologically plausible neural architecture
- Unsupervised neural controller for Reinforcement Learning action-selection: Learning to represent knowledge
- Human-level control through deep reinforcement learning
- Deep Reinforcement Learning for constructing meaning by ‘babbling’
- Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning â€¦

## Reliability

## Representation

## Representation Learning

- Deep Representation Learning with Target Coding Supplementary Material
- Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
- Training Stacked Denoising Autoencoders for Representation Learning
- End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
- Imaging and representation learning of solar radio spectrums for classification
- Representation Learning with Deep Extreme Learning Machines for Efficient Image Set Classification
- Unsupervised domain adaptation via representation learning and adaptive classifier learning
- On Invariance and Selectivity in Representation Learning

## Restricted Boltzmann Machine

- To be Bernoulli or to be Gaussian, for a Restricted Boltzmann Machine
- Deep neural network based load forecast
- Expected energy-based restricted Boltzmann machine for classification
- A Noisy-Or Discriminative Restricted Boltzmann Machine for Recognizing Handwriting Style Development
- Deep Tempering
- A Novel Inference of a Restricted Boltzmann Machine
- Deep Model for Classification of Hyperspectral image using Restricted Boltzmann Machine
- Classification Restricted Boltzmann Machine for comprehensible credit scoring model
- Deep Correspondence Restricted Boltzmann Machine for Cross-modal Retrieval
- A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling
- An Evolutionary Approximation to Contrastive Divergence in Convolutional Restricted Boltzmann Machines
- Stochastic Spectral Descent for Restricted Boltzmann Machines
- Advanced Mean Field Theory of Restricted Boltzmann Machine
- Conditional Restricted Boltzmann Machines for Multi-label Learning with Incomplete Labels
- Fuzzy Restricted Boltzmann Machine and Its Fast Learning Algorithm
- Mask selective regularization for restricted Boltzmann machines

## Restricted Boltzmann Machines

- Learning motion-difference features using Gaussian restricted Boltzmann machines for efficient human action recognition
- Learning ensemble classifiers via restricted Boltzmann machines
- Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks
- A Fully Pipelined FPGA Architecture of a Factored Restricted Boltzmann Machine Artificial Neural Network
- Difference representation learning using stacked restricted Boltzmann machines for change detection in Sar images
- Maximum Reconstruction Probability Training Of Restricted Boltzmann Machines With Auxiliary Function Approach
- High-Order Semi-RBMs and Deep Gated Neural Networks for Feature Interaction Identification and Non-Linear Semantic Indexing
- Periocular Recognition using Unsupervised Convolutional Rbm Feature Learning
- A 3d model recognition mechanism based on deep boltzmann machines
- Scalable Learning for Restricted Boltzmann Machines
- Atomic Energy Models For Machine Learning: Atomic Restricted Boltzmann Machines
- A Distributed Implementation of Training the Restricted Boltzmann Machine
- Energy Based Models and Boltzmann Machines (Cont.)
- Deep Narrow Boltzmann Machines are Universal Approximators
- Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization
- An automatic setting for training restricted boltzmann machine
- An Algorithm of Quantum Restricted Boltzmann Machine Network Based on Quantum Gates and Its Application
- Restricted Boltzmann Machines with Svm for Object Recognitionâ‹†
- Voice Conversion Using Rnn Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines
- Investigating the Consistency and Convexity of Restricted Boltzmann Machine Learning
- Stochastic Spectral Descent for Restricted Boltzmann Machines
- Conditional Restricted Boltzmann Machines for Multi-label Learning with Incomplete Labels
- Mask selective regularization for restricted Boltzmann machines

## Restricted Bolzmann Machines

## Retail

## Retinal Images

## Reverse Annealing

## Review

- Applying skip-gram word estimation and SVM-based classification for opinion mining Vietnamese food places text reviews
- A Review of Methods for the Calculation of Solution Free Energies and the Modelling of Systems in Solution
- Unsupervised Deep Learning: A Short Review
- Efficient Machine Learning for Big Data: A Review

## Risk Minimization

## Road Detection

## Robot

- Robot Learning Manipulation Action Plans by â€œWatchingâ€ Unconstrained Videos from the World Wide Web
- Robotic Grasping System Using Convolutional Neural Networks
- Advanced Robotic Grasping System Using Deep Learning
- A survey of research on cloud robotics and automation
- Robust face recognition via transfer learning for robot partner
- Robot team learning enhancement using Human Advice

## Robotics

- Multimodal integration learning of robot behavior using deep neural networks
- Survey and Implementation of Computer Vision Techniques for Humanoid Robots
- Helping robots see the big picture
- Deep learning for detecting robotic grasps
- Control In A Safe Set: Addressing Safety In Human-robot Interactions
- A survey of research on cloud robotics and automation

## Robust

- Robust face recognition via transfer learning for robot partner
- Transferring Rich Feature Hierarchies for Robust Visual Tracking
- Robust Tracking via Convolutional Networks without Learning
- Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
- Robust Excitation-based Features For Automatic Speech Recognition
- DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking
- Supervised descent method with low rank and sparsity constraints for robust face alignment
- Robust people counting using sparse representation and random projection
- Simple, Accurate, and Robust Nonparametric Blind Super-Resolution

## Salient

## Sampling

## Sar Data

## Scalability

- Scaling Distributed Machine Learning with the Parameter Server
- Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization
- Scalable, High-Quality Object Detection
- Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning
- DeepSpeech: Scaling up end-to-end speech recognition

## Scene Classification

- Scene Classification Based on Single-layer Sae and Svm
- Dynamic texture and scene classification by transferring deep image features
- DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification
- Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks

## Scene Recognition

- Deep Deconvolutional Networks for Scene Parsing
- Scene Recognition Using Mid-level features from Cnn
- Scene Recognition
- Scene Recognition by Manifold Regularized Deep Learning Architecture

## Scheduling

## Score Function

- Score Function Features for Discriminative Learning: Matrix and Tensor Framework
- Score Function Features for Discriminative Learning

## Sda

## Search

- Query expansion for mixed-script information retrieval
- Query Expansion for Multi-script Information Retrieval
- A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval
- Enhanced Higgs to $\ tau^+\ tau^-$ Searches with Deep Learning
- Implicitly Learning a User Interest Profile for Personalization of Web Search Using Collaborative Filtering
- Research on deep neural network’s hidden layers in phoneme recognition
- Cross-modal Retrieval with Correspondence Autoencoder
- Deep Search with Attribute-aware Deep Network
- Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning
- Beginning at the End: The outcome spaces framework to guide purposive transdisciplinary research
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
- The Research of Event Detection and Characterization Technology of Ticket Gate in the Urban Rapid Rail Transit
- A survey of research on cloud robotics and automation
- Entity-centric search: querying by entities and for entities
- The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid
- Deep Learning for Web Search and Natural Language Processing
- Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research
- Replicating the Research of the Paper:â€œApplication of Artificial Neural Network in Detection of Probing Attacksâ€
- Enhanced Higgs Boson to Ï„+ Ï„âˆ’ Search with Deep Learning
- Threshold concepts in the Scholarship of Teaching and Learning: a phenomenological study of educational leaders in a Canadian research-intensive university

## Security

- Deep Learning of Behaviors for Security
- Replicating the Research of the Paper:â€œApplication of Artificial Neural Network in Detection of Probing Attacksâ€

## Segmentation

- Fully Convolutional Networks for Semantic Segmentation
- Fully Convolutional Neural Networks for Crowd Segmentation
- Hypercolumns for Object Segmentation and Fine-grained Localization
- Deep convolutional filter banks for texture recognition and segmentation
- Hybrid Graphical Model for Semantic Image Segmentation
- Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation
- segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation
- Deep Hierarchical Parsing for Semantic Segmentation
- Deep learning for automatic localization, identification, and segmentation of vertebral bodies in volumetric Mr images
- Deep convolutional networks for pancreas segmentation in Ct imaging

## Self-Informed

## Semantic

- Cnu System in Ntcir-11 IMine Task
- Tuta1 at the Ntcir-11 IMine Task
- Hybrid Graphical Model for Semantic Image Segmentation
- Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation
- Open Domain Question Answering via Semantic Enrichment
- Learning Semantic Hierarchies: A Continuous Vector Space Approach
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation
- Compositional Distributional Semantics with Long Short Term Memory
- Deep Hierarchical Parsing for Semantic Segmentation
- Deep Structured Semantic Model Produced Using Click-Through Data
- Learning Document Semantic Representation with Hybrid Deep Belief Network
- Lig at TRECVid 2014: Semantic Indexing

## Semantic Indexing

## Semantics

- Learning Multi-Relational Semantics Using Neural-Embedding Models
- Compositional Distributional Semantics with Long Short Term Memory

## Semantix Indexing

## Semi-Supervised

- Extended Semi-supervised Fuzzy Learning Method for Nonlinear Outliers via Pattern Discovery
- Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation

## Sensor Data

- Predictive Analytics of Sensor Data Using Distributed Machine Learning Techniques
- Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data

## Sensory

## Sentiment

- Modelling User Affect and Sentiment in Intelligent User Interfaces: A Tutorial Overview

## Sentiment Analysis

- Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis
- Adaptive recursive neural network for target-dependent twitter sentiment classification
- Deep convolutional neural networks for sentiment analysis of short texts
- Recursive Deep Learning for Sentiment Analysis over Social Data
- Learning Bilingual Embedding Model for Cross-Language Sentiment Classification
- Visual Sentiment Prediction with Deep Convolutional Neural Networks

## Sequence Learning

- Sequence to Sequence Learning with Neural Networks
- On the Problem of Features Variability in Sequence Learning Problems

## Sequence Modelling

## Shape Classification

## Shearlet Transform

## Sigmoid

## Sign Language

## Signal Processing

## Similarity Learning

## Simplicity

## Simulation

- GPU Accelerated Computation and Real-time Rendering of Cellular Automata Model for Spatial Simulation
- Using High-fidelity Simulation as a Learning Strategy in an Undergraduate Intensive Care Course
- Entrepreneurship Support Based on Mixed Bio-Artificial Neural Network Simulator (esbbann)

## Singular Value Decomposition

## Sketch Recognition

## Smart City

## Smart Homes

## Smoothing

- Single image super-resolution via L0 image smoothing
- Single Image Super-Resolution via Image Smoothing

## Social

- Detecting spammers on social Networks

## Social Network

## Soft Computing

## Softmax

- Quaternion softmax classifier
- An Image Retrieval Method for Binary Images Based on Dbn and Softmax Classifier

## Software

## Sosial Network

## Sound

- Recognition Of Acoustic Events Using Deep Neural Networks
- Audio Concept Classification With Hierarchical Deep Neural Networks
- Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training
- Estimating Tract Variables from Acoustics via Neural Networks
- Supervised non-negative matrix factorization for audio source separation
- Multilabel Sound Event Classification with Neural Networks
- Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition

## Sound Retrieval

## Spam

## Sparse

- Spatially Constrained Sparse Coding Scheme for Natural Scene Categorization
- Hierarchical Recognition System for Target Recognition from Sparse Representations
- Sparse Neural Networks
- Robust people counting using sparse representation and random projection

## Sparseness

- A Winner-Take-All Method for Training Sparse Convolutional Autoencoders
- Exploiting sparseness in training deep neural networks
- Alternate Layer Sparsity and Intermediate Fine-tuning for Deep Autoencoders
- A linear approach for sparse coding by a two-layer neural network
- Static hand gesture recognition using stacked Denoising Sparse Autoencoders
- Compute Less to Get More: Using Orc to Improve Sparse Filtering
- Spatially-sparse convolutional neural networks
- Hsr: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection
- Analyzing sparse dictionaries for online learning with kernels
- Sparse Representations, Numerical Linear Algebra, and Optimization
- Provable Methods for Training Neural Networks with Sparse Connectivity
- Sparse Deep Stacking Network for Image Classification

## Sparsity

- Supervised descent method with low rank and sparsity constraints for robust face alignment

## Spatial

- The Spatial Complexity of Inhomogeneous Multi-layer Neural Networks
- Spatially Constrained Sparse Coding Scheme for Natural Scene Categorization
- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- Monte Carlo Integration Using Spatial Structure of Markov Random Field
- Method and System for Predicting Spatial and Temporal Distributions of Therapeutic Substance Carriers
- Learning by Observation Using Qualitative Spatial Relations

## Spatial Planning

## Spatially

## Spatio-Temporal

- Learning spatio-temporal features for action recognition from the side of the video
- Spatio-Temporal Moving Object Proposals
- Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition
- Scalable Hardware Efficient Deep Spatio-Temporal Inference Networks
- Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism

## Spectral

- Stochastic Spectral Descent for Restricted Boltzmann Machines
- Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network
- Deep Convolutional Neural Networks for Hyperspectral Image Classification

## Spectral Classification

## Speech

- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Unidirectional Long Short-term Memory Recurrent Neural Network With Recurrent Output Layer For Low-latency Speech â€¦
- Noisy Training for Deep Neural Networks in Speech Recognition
- Deep Multimodal Learning for Audio-Visual Speech Recognition
- A Fast Learning Method for the Multi-layer Perceptron in Automatic Speech Recognition Systems
- F0 Modeling In Hmm-Based Speech Synthesis System Using Deep Belief Network
- Robust Excitation-based Features For Automatic Speech Recognition
- Machine Learning in Automatic Speech Recognition: A Survey
- Deep learning for speech classification and speaker recognition
- Speech Separation based on Deep Belief Network
- Speech emotion recognition with unsupervised feature learning

## Speech Recognition

- Should deep neural nets have ears? The role of auditory features in deep learning approaches
- Increasing Deep Neural Network Acoustic Model Size for Large Vocabulary Continuous Speech Recognition
- Deep learning vector quantization for acoustic information retrieval
- A Deep Learning Pipeline for Image Understanding and Acoustic Modeling
- Parallel Deep Neural Network Training for LVCSR Tasks using Blue Gene/Q
- 1-Bit Stochastic Gradient Descent and its Application to Data-Parallel Distributed Training of Speech DNNs
- Deep Learning for Emotional Speech Recognition
- Improving deep neural network acoustic models using generalized maxout networks
- RASR/NN: The RWTH neural network toolkit for speech recognition
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
- First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs
- A historical perspective of speech recognition
- Improving deep neural networks for LVCSR using dropout and shrinking structure
- A comparison of two optimization techniques for sequence discriminative training of deep neural networks
- Using Deep Belief Networks for Vector-Based Speaker Recognition
- Fine context, low-rank, softplus deep neural networks for mobile speech recognition
- Statistical Parametric Speech Synthesis using Weighted Multi-distribution Deep Belief Network
- Boundary Contraction Training for Acoustic Models based on Discrete Deep Neural Networks
- Contrastive auto-encoder for phoneme recognition
- Deep Learning of Orthographic Representations in Baboons
- Speaker adaptation of deep neural network based on discriminant codes
- Deep learning of split temporal context for automatic speech recognition
- Deep Generative and Discriminative Models for Speech Recognition
- Spoken emotion recognition using deep learning
- RASR/NN: THE RWTH NEURAL NETWORK TOOLKIT FOR SPEECH RECOGNITION
- AUDIO CONCEPT CLASSIFICATION WITH HIERARCHICAL DEEP NEURAL NETWORKS
- Noise-Robust Speech Recognition Using Deep Neural Network
- Acceleration Strategies for Speech Recognition Based on Deep Neural Networks
- Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training
- Deep convolutional neural networks for large-scale speech tasks
- A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis
- Improving Acoustic Model for Vietnamese Large Vocabulary Continuous Speech Recognition System Using Deep Bottleneck Features
- The relation of eye gaze and face pose: Potential impact on speech recognition
- Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments
- Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks
- Computational modeling and validation of the motor contribution to speech perception
- Deep Neural Networks For Spoken Dialog Systems
- Neural Network Based Pitch Tracking In Very Noisy Speech
- An Investigation of Implementation and Performance Analysis of Dnn Based Speech Synthesis System
- Ensemble Learning Approaches in Speech Recognition
- Raw Speech Signal-based Continuous Speech Recognition using Convolutional Neural Networks
- Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array
- Dysarthric Speech Recognition Using a Convolutive Bottleneck Network
- Cross-language speech attribute detection and phone recognition for Tibetan using deep learning
- Mapping between ultrasound and vowel speech using Dnn framework
- Improving generation performance of speech emotion recognition by denoising autoencoders
- Research on deep neural network’s hidden layers in phoneme recognition
- Cross-language transfer learning for deep neural network based speech enhancement
- Performance evaluation of deep bottleneck features for spoken language identification
- Multiple time-span feature fusion for deep neural network modeling
- Investigation of stochastic Hessian-Free optimization in Deep neural networks for speech recognition
- Phonotactic language recognition based on Dnn-hmm acoustic model
- Labeling unsegmented sequence data with Dnn-hmm and its application for speech recognition
- Building an ensemble of Cd-dnn-hmm acoustic model using random forests of phonetic decision trees
- Speaker adaptation of hybrid Nn/hmm model for speech recognition based on singular value decomposition
- Decision tree based state tying for speech recognition using Dnn derived embeddings
- Deep belief network based Crf for spoken language understanding
- A fusion approach to spoken language identification based on combining multiple phone recognizers and speech attribute detectors
- Patch-Based Models of Spectrogram Edges for Phone Classification
- Cross-Dialectal Voice Conversion with Neural Networks
- Trope
- Non-negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition
- Speech Emotion Recognition Using Cnn
- Joint Phoneme Segmentation Inference and Classification using CRFs
- Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
- Supervised Speech Separation And Processing
- Deep Neural Network Based Speech Separation for Robust Speech Recognition
- Speech Separation of A Target Speaker Based on Deep Neural Networks
- Extracting Deep Bottleneck Features For Visual Speech Recognition
- A critical examination of deep learning approaches to automated speech recognition
- End-to-end Continuous Speech Recognition using Attention-based Recurrent Nn: First Results
- Automatic Speech Recognition: A Deep Learning Approach
- Deep neural network adaptation for children’s and adults’ speech recognition
- Vocal Tract Length Normalisation Approaches To Dnn-based Children’s And Adults’speech Recognition
- Audio-visual speech recognition using deep learning
- DeepSpeech: Scaling up end-to-end speech recognition
- Learning linearly separable features for speech recognition using convolutional neural networks
- Speech Enhancement Based on Analysisâ€“Synthesis Framework With Improved Pitch Estimation and Spectral Envelope Enhancement
- Improved Mispronunciation Detection with Deep Neural Network Trained Acoustic Models and Transfer Learning based Logistic Regression Classifiers
- Soft context clustering for F0 modeling in HMM-based speech synthesis
- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Fast adaptation of deep neural network based on discriminant codes for speech recognition
- Acoustic Model Structuring for Improving Automatic Speech Recognition Performance
- Noisy Training for Deep Neural Networks in Speech Recognition
- Deep Multimodal Learning for Audio-Visual Speech Recognition
- A Fast Learning Method for the Multi-layer Perceptron in Automatic Speech Recognition Systems
- Robust Excitation-based Features For Automatic Speech Recognition
- Machine Learning in Automatic Speech Recognition: A Survey

## Speech Synthesis

- Parametric Speech Synthesis Using Local and Global Sparse Gaussian
- F0 Modeling In Hmm-Based Speech Synthesis System Using Deep Belief Network

## Stability

## Statistical Inference

- Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels

## Stochastic

- Stochastic Spectral Descent for Restricted Boltzmann Machines
- Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM
- On Graduated Optimization for Stochastic Non-Convex Problems
- GSNs: Generative Stochastic Networks

## Stochastic Gradient

- Mean-normalized stochastic gradient for large-scale deep learning
- MEAN-NORMALIZED STOCHASTIC GRADIENT FOR LARGE-SCALE DEEP LEARNING
- Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent
- Stochastic Descent Analysis of Representation Learning Algorithms
- Deep learning with Elastic Averaging Sgd
- Adasecant: Robust Adaptive Secant Method for Stochastic Gradient
- Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods

## Stochastic Gradient Descent

- 1-Bit Stochastic Gradient Descent and its Application to Data-Parallel Distributed Training of Speech DNNs
- On Parallelizability of Stochastic Gradient Descent for Speech DNNs
- Exploring one pass learning for deep neural network training with averaged stochastic gradient descent
- Asynchronous stochastic optimization for sequence training of deep neural networks
- Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent

## Stochastic Optimization

## Strategiesx

## Structured Networks

## Study

- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Constrained Extreme Learning Machines: A Study on Classification Cases
- Predicting Alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks
- Masterarbeit: Big Data and Machine Learning: A Case Study with Bump Boost
- Study on Binary Multilayer Neural Networks with Ebp Algorithm on Image Classification
- Threshold concepts in the Scholarship of Teaching and Learning: a phenomenological study of educational leaders in a Canadian research-intensive university

## Subspace Analysis

## Subspace Learning

## Summarization

- Video summarization based on Subclass Support Vector Data Description
- Ranking with Recursive Neural Networks and Its Application to Multi-document Summarization
- Co-Regularized Deep Representations for Video Summarization

## Supervised

- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Explicit knowledge extraction in information-theoretic supervised multi-layered Som
- Unsupervised dictionary extraction of bird vocalizations and new tools on assessing and visualizing bird activity
- Extended Semi-supervised Fuzzy Learning Method for Nonlinear Outliers via Pattern Discovery
- Shoe: Supervised Hashing with Output Embeddings
- Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation
- Unsupervised Deep Learning: A Short Review
- Fingerprint Image Enhancement Using Unsupervised Hierarchical Feature Learning
- Unsupervised Deep Network Pretraining via Human Design
- Overcoming Intractability in Unsupervised Learning (Invited Talk)}}”, author = “S Arora, EW Mayr, N Ollinger
- Deep Transfer Network: Unsupervised Domain Adaptation
- Why Does Unsupervised Deep Learning WORK?-Aperspective From Group Theory
- Supervised descent method with low rank and sparsity constraints for robust face alignment
- Soft sensor development for nonlinear and timeâ€varying processes based on supervised ensemble learning with improved process state partition
- Unsupervised word sense induction using rival penalized competitive learning
- Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Speech emotion recognition with unsupervised feature learning
- Unsupervised domain adaptation via representation learning and adaptive classifier learning

## Supervised Learning

## Support Vector Machine

- Deep Twin Support Vector Machine
- Continuous Hyper-parameter Learning for Support Vector Machines

## Support Vector Machines

- Deep learning of support vector machines with class probability output networks
- Continuous Hyper-parameter Learning for Support Vector Machines

## Surrogates

## Survey

- A tutorial survey of architectures, algorithms, and applications for deep learning
- A brief survey on deep belief networks and introducing a new object oriented MATLAB toolbox (DeeBNet)
- Neural Networks: A Review
- Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
- Facial Feature Point Detection: A Comprehensive Survey
- Visual Domain Adaptation: A Survey of Recent Advances
- A Survey of Regularization Methods for Deep Neural Network
- An Adaptive Approach of Tamil Character Recognition Using Deep Learning with Big Data-A Survey
- Object Recognition Using Deep Neural Networks: A Survey
- Survey of Local Descriptor of Object Recognition System based on Rgb-d Images
- Non-Distortion-Specific no-reference image quality assessment: A survey
- Comparative Study Of Machine Learning Techniques For Supervised Classification Of Biomedical Data
- A survey of research on cloud robotics and automation
- Transfer Learning using Computational Intelligence: A Survey
- Machine Learning in Automatic Speech Recognition: A Survey

## Svm

- How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
- An Innovative Svm for Wheat Seed Quality Estimationâ‹†
- Detection of Alzheimer’s disease using group lasso SVM-based region selection

## Swarm Optimization

- Achieving Consistent Near-Optimal Pattern Recognition Accuracy Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks
- The Synergistic Combination of Particle Swarm Optimization and Fuzzy Sets to Design Granular Classifier

## Synonym Extraction

## Target Coding

## Target Detection

## Temporal

- Accelerated gradient temporal difference learning algorithms
- Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition
- HFirst: A Temporal Approach to Object Recognition
- Learning invariant object recognition from temporal correlation in a hierarchical network
- Scalable Hardware Efficient Deep Spatio-Temporal Inference Networks
- Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
- Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets
- Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism

## Temporal Dependencies

## Tensor

## Term

- Accurate localized short term weather prediction for renewables planning
- Retrieval Term Prediction Using Deep Belief Networks
- Deep Sentence Embedding Using the Long Short Term Memory Network: Analysis and Application to Information Retrieval
- Compositional Distributional Semantics with Long Short Term Memory

## Text Classification

- Deep Belief Networks and Biomedical Text Categorisation
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

## Text Recognition

## Texture Recognition

## Theano

## Theory

- Adaptive Information-Theoretical Feature Selection for Pattern Classification
- The atoms of neural computation
- On The Dynamical Nature Of Computation
- Supplementary Material: On the Number of Linear Regions of Deep Neural Networks
- Why does Deep Learning work?-A perspective from Group Theory
- Advanced Mean Field Theory of Restricted Boltzmann Machine
- Brain as an Emergent Finite Automaton: A Theory and Three Theorems
- Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters
- Why Does Unsupervised Deep Learning WORK?-Aperspective From Group Theory
- Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory
- Multithreshold Entropy Linear Classifier: Theory and Applications

## Thermodynamics

## Thin Deep Networks

## Time Series

- A review of unsupervised feature learning and deep learning for time-series modeling
- Learning Methods for Variable Selection and Time Series Prediction
- Structured Recurrent Temporal Restricted Boltzmann Machines
- Deep Multimodal Fusion: Combining Discrete Events and Continuous Signals
- Query Optimization in Heterogeneous Cpu/gpu Environment for Time Series Databases
- Temporal Dropout of Changes Approach to Convolutional Learning of Spatio-Temporal Features
- Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video
- Dual-domain Hierarchical Classification of Phonetic Time Series
- Support Vector-Based Algorithms with Weighted Dynamic Time Warping Kernel Function for Time Series Classification
- Error Modeling Approach to Improve Time Series Forecasters

## Tongue

## Tool

## Tools

## Topic Modelling

- A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data
- A Novel Neural Topic Model and Its Supervised Extension

## Traffic

- Traffic Flow Prediction With Big Data: A Deep Learning Approach
- Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
- Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning
- DeepSense: A novel learning mechanism for traffic prediction with taxi Gps traces
- An Online-Traffic-Prediction Based Route Finding Mechanism for Smart City
- A novel pLSA based Traffic Signs Classification System

## Traffic Prediction

## Traffic Sign

- Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature
- A novel pLSA based Traffic Signs Classification System

## Transcription

## Transductive

## Transfer Learning

- Transfer Learning for Video Recognition with Scarce Training Data
- Deep Multi-Instance Transfer Learning
- Representation Sharing and Transfer in Deep Neural Networks
- Improved Mispronunciation Detection with Deep Neural Network Trained Acoustic Models and Transfer Learning based Logistic Regression Classifiers
- Robust face recognition via transfer learning for robot partner
- Transfer Learning using Computational Intelligence: A Survey

## Tree Structure

## Tree Structures

## Trends

## Ultrasound

- Mapping between ultrasound and vowel speech using Dnn framework
- High-definition 3d Image Processing Technology for Ultrasound Diagnostic Scanners

## Una

## Unsupervised

- Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering
- Unsupervised Deep Learning: A Short Review
- Fingerprint Image Enhancement Using Unsupervised Hierarchical Feature Learning
- Unsupervised Deep Network Pretraining via Human Design
- Overcoming Intractability in Unsupervised Learning (Invited Talk)}}”, author = “S Arora, EW Mayr, N Ollinger
- Deep Transfer Network: Unsupervised Domain Adaptation
- Why Does Unsupervised Deep Learning WORK?-Aperspective From Group Theory
- Unsupervised word sense induction using rival penalized competitive learning
- Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics
- Speech emotion recognition with unsupervised feature learning
- Unsupervised domain adaptation via representation learning and adaptive classifier learning

## Unsupervised Learning

- Unsupervised learning of hierarchical representations with convolutional deep belief networks
- Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations
- Deep unsupervised network for multimodal perception, representation and classification
- Unsupervised Deep Haar Scattering on Graphs
- Unsupervised Learning of Semantics of Object Detections for Scene Categorization
- Robot Learning Manipulation Action Plans by â€œWatchingâ€ Unconstrained Videos from the World Wide Web
- Pedestrian Detection Based on Multi-Stage Unsupervised Learning
- From neural Pca to deep unsupervised learning
- Learning Face Representation from Scratch
- Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
- Unsupervised feature learning on monaural Doa estimation using convolutional deep belief networks
- Unsupervised generation of context-relevant training-sets for visual object recognition employing multilinguality
- Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework
- Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition
- Unsupervised Domain Adaptation with Feature Embeddings
- Unsupervised Learning of Spatiotemporally Coherent Metrics
- An Analysis of Unsupervised Pre-training in Light of Recent Advances
- C-SVDDNet: An Effective Single-Layer Network for Unsupervised Feature Learning
- Fingerprint Enhancement Using Unsupervised Hierarchical Feature Learning
- Unsupervised Feature Learning for Dense Correspondences across Scenes

## User Authentication

## User Interface

## User Interfaces

## Vehicle

- Vehicle Logo Recognition System Based on Convolutional Neural Networks With a Pretraining Strategy
- Vehicle Detection in Aerial Imagery: A small target detection benchmark

## Vehicle Classification

## Vehicle Classificationx

## Vehicle Recognition

## Video

- Challenge Huawei challenge: Fusing multimodal features with deep neural networks for Mobile Video Annotation
- Reducing structure of deep Convolutional Neural Networks for Huawei Accurate and Fast Mobile Video Annotation Challenge
- Modeling Video Dynamics with Deep Dynencoder
- Large-scale video classification with convolutional neural networks
- Machine Learning in Intelligent Video and Automated Monitoring
- Transfer Learning for Video Recognition with Scarce Training Data
- Effects on learning of multimedia animation combined with multidimensional concept maps
- MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
- A Study of Feature Combination in Gesture Recognition with Kinect
- Video Event Detection via Multi-modality Deep Learning
- Semantic parsing for priming object detection in indoors Rgb-d scenes
- Fusing Music and Video Modalities Using Multi-timescale Shared Representations
- Mask Assisted Object Coding with Deep Learning for Object Retrieval in Surveillance Videos
- Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video
- Automatic face annotation in Tv series by video/script alignment
- Building a Post-Compression Region-of-Interest Encryption Framework for Existing Video Surveillance Systems
- Robot Learning Manipulation Action Plans by â€œWatchingâ€ Unconstrained Videos from the World Wide Web
- C3d: Generic Features for Video Analysis
- Video Event Detection via Multi-modality Deep Learning
- Audio-based annnotatoion of video
- Translating Videos to Natural Language Using Deep Recurrent Neural Networks
- Learning features and their transformations from natural videos
- Shape Feature Encoding via Fisher Vector for Efficient Fall Detection in Depth-Videos
- Video summarization based on Subclass Support Vector Data Description
- Co-Regularized Deep Representations for Video Summarization
- Dense 3d Face Alignment from 2d Videos in Real-Time
- Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
- Automated Construction of Visual-Linguistic Knowledge via Concept Learning from Cartoon Videos
- Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research
- Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism
- EmoNets: Multimodal deep learning approaches for emotion recognition in video
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

## Videos

- Learning features and their transformations from natural videos
- Shape Feature Encoding via Fisher Vector for Efficient Fall Detection in Depth-Videos
- Dense 3d Face Alignment from 2d Videos in Real-Time
- Automated Construction of Visual-Linguistic Knowledge via Concept Learning from Cartoon Videos
- Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos

## Vision

## Visual

- Transferring Rich Feature Hierarchies for Robust Visual Tracking
- Indexing Images for Visual Memory by Using Dnn Descriptorsâ€“Preliminary Experiments
- Deep Multimodal Learning for Audio-Visual Speech Recognition
- Two Dimensional Hashing for Visual Tracking
- A Hmax with Llc for visual recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle
- The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition
- Automated Construction of Visual-Linguistic Knowledge via Concept Learning from Cartoon Videos
- DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking
- Learning Shared, Discriminative, and Compact Representations for Visual Recognition
- Domain Adaptation for Visual Recognition
- Learning Discriminative Feature Representations for Visual Categorization
- Exploring co-learning behavior of conference participants with visual network analysis of Twitter data
- I Can Has Cheezburger? A Nonparanormal Approach to Combining Textual and Visual Information for Predicting and Generating Popular Meme Descriptions

## Visual Memory

## Vocal

- Sound Retrieval From Vocal Imitation Queries Based On Deep Neural Networks

## Voice Recognition

## Vowel

## Weather Prediction

## Web Mining

## Web Search

## Web Spam

## Weed Classification

## Weld

## Wind Power

## Word Embeddings

## Word Segmentation

## Word Sense

# BIBLIOGRAPHY

@misc{2014AAGarcezTRBesoldLdeRaedtPFÃ¶ldiakPHitzler, title = {Neural-Symbolic Learning and Reasoning: Contributions and Challenges}, author = {AA Garcez, TR Besold, L de Raedt, P FÃ¶ldiak, P Hitzler} } @misc{2014AAravkinLDengGHeigoldTJebaraDKanevski, title = {Log-Linear Models, Extensions and Applications}, author = {A Aravkin, L Deng, G Heigold, T Jebara, D Kanevski} } @misc{2014ABergamoLBazzaniDAnguelovLTorresani, title = {Self-taught Object Localization with Deep Networks}, author = {A Bergamo, L Bazzani, D Anguelov, L Torresani} } @misc{2014AChoromanskaMHenaffMMathieuGBArous, title = {The Loss Surface of Multilayer Networks}, author = {A Choromanska, M Henaff, M Mathieu, GB Arous} } @misc{2014ADeleforgeFForbesSBaRHoraud, title = {Hyper-Spectral Image Analysis with Partially-Latent Regression and Spatial Markov Dependencies}, author = {A Deleforge, F Forbes, S Ba, R Horaud} } @misc{2014ADosovitskiyJTSpringenbergTBrox, title = {Learning to Generate Chairs with Convolutional Neural Networks}, author = {A Dosovitskiy, JT Springenberg, T Brox} } @misc{2014ADroniouSIvaldiOSigaud, title = {Deep unsupervised network for multimodal perception, representation and classification}, author = {A Droniou, S Ivaldi, O Sigaud} } @misc{2014ADundarJJinVGokhaleBMartiniECulurciello, title = {Memory Access Optimized Scheduling Scheme for DCNNs on a Mobile Processor}, author = {A Dundar, J Jin, V Gokhale, B Martini, E Culurciello} } @misc{2014AFinkbinerRLauerJRice, title = {Predicting Likelihood of Hospitalization with Subset-Filtered Emerging Patterns}, author = {A Finkbiner, R Lauer, J Rice} } @misc{2014AGaskellRMills, title = {The quality and reputation of open, distance and e-learning: what are the challenges?}, author = {A Gaskell, R Mills} } @misc{2014AHannunCCaseJCasperBCatanzaroGDiamos, title = {DeepSpeech: Scaling up end-to-end speech recognition}, author = {A Hannun, C Case, J Casper, B Catanzaro, G Diamos} } @misc{2014AJYepesAMacKinlayJBedoRGarnaviQChen, title = {Deep Belief Networks and Biomedical Text Categorisation}, author = {AJ Yepes, A MacKinlay, J Bedo, R Garnavi, Q Chen} } @misc{2014AJainJTompsonYLeCunCBregler, title = {MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation}, author = {A Jain, J Tompson, Y LeCun, C Bregler} } @misc{2014AJainSAteySVinayakVSrivastava, title = {Cancerous Cell Detection Using Histopathological Image Analysis}, author = {A Jain, S Atey, S Vinayak, V Srivastava} } @misc{2014AJalalvandFTriefenbachKDemuynckJPMartens, title = {Robust continuous digit recognition using reservoir computing}, author = {A Jalalvand, F Triefenbach, K Demuynck, JP Martens} } @misc{2014AKNoor, title = {Potential of Cognitive Computing and Cognitive Systems}, author = {AK Noor} } @misc{2014AKnittelABlair, title = {Sparse, guided feature connections in an Abstract Deep Network}, author = {A Knittel, A Blair} } @misc{2014AMontaltoGTessitoreRPrevete, title = {A linear approach for sparse coding by a two-layer neural network}, author = {A Montalto, G Tessitore, R Prevete} } @misc{2014ANandaROmanwarBDeshpande, title = {Implicitly Learning a User Interest Profile for Personalization of Web Search Using Collaborative Filtering}, author = {A Nanda, R Omanwar, B Deshpande} } @misc{2014ANguyenJYosinskiJClune, title = {Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images}, author = {A Nguyen, J Yosinski, J Clune} } @misc{2014AOIbraheem, title = {Karush-Kuhn-Tucker meets David Hubel and Torsten Weisel through Gabriel Kreiman and Andrew Ng: A connection between highlights of constrained convex..}, author = {AO Ibraheem} } @misc{2014AOTANGKELUYWANGJIEHUANGHLI, title = {A Real-time Hand Posture Recognition System Using Deep Neural Networks}, author = {AO TANG, KE LU, Y WANG, JIE HUANG, H LI} } @misc{2014AOhri, title = {R for Cloud Computing}, author = {A Ohri} } @misc{2014APaulSVenkatasubramanian, title = {Why does Deep Learning work?-A perspective from Group Theory}, author = {A Paul, S Venkatasubramanian} } @misc{2014APunjaniPAbbeel, title = {Machine Learning for Helicopter Dynamics Models}, author = {A Punjani, P Abbeel} } @misc{2014ARodrÃguezSÃ¡nchezHNeumannJPiater, title = {Beyond Simple and Complex Neurons: Towards Intermediate-level Representations of Shapes and Objects}, author = {A RodrÃguez-SÃ¡nchez, H Neumann, J Piater} } @misc{2014ARomeroNBallasSEKahouAChassangCGatta, title = {FitNets: Hints for Thin Deep Nets}, author = {A Romero, N Ballas, SE Kahou, A Chassang, C Gatta} } @misc{2014ARomeroPRadevaCGatta, title = {Meta-parameter free unsupervised sparse feature learning}, author = {A Romero, P Radeva, C Gatta} } @misc{2014ASRazavianHAzizpourAMakiJSullivanCHEk, title = {Persistent Evidence of Local Image Properties in Generic ConvNets}, author = {AS Razavian, H Azizpour, A Maki, J Sullivan, CH Ek} } @misc{2014ASchwarzCHuemmerRMaasWKellermann, title = {Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments}, author = {A Schwarz, C Huemmer, R Maas, W Kellermann} } @misc{2014ASinghARajVKGupta, title = {Scene Recognition Using Mid-level features from Cnn}, author = {A Singh, A Raj, VK Gupta} } @misc{2014ASinghARajVKGuptaSceneRecognition, title = {Scene Recognition}, author = {A Singh, A Raj, VK Gupta} } @misc{2014ASironiETÃ¼retkenVLepetitPFua, title = {Multiscale Centerline Detection}, author = {A Sironi, E TÃ¼retken, V Lepetit, P Fua} } @misc{2014ASuzani, title = {Automatic vertebrae localization, identification, and segmentation using deep learning and statistical models}, author = {A Suzani} } @misc{2014AUnterwegerKVanRyckegemDEngelAUhl, title = {Building a Post-Compression Region-of-Interest Encryption Framework for Existing Video Surveillance Systems}, author = {A Unterweger, K Van Ryckegem, D Engel, A Uhl} } @misc{2014BAhnJParkISKweon, title = {Real-time Head Orientation from a Monocular Camera using Deep Neural Network}, author = {B Ahn, J Park, IS Kweon} } @misc{2014BCKoJHJungJYNam, title = {View-independent object detection using shared local features}, author = {BC Ko, JH Jung, JY Nam} } @misc{2014BChenQYinPGuo, title = {A Study of Deep Belief Network Based Chinese Speech Emotion Recognition}, author = {B Chen, Q Yin, P Guo} } @misc{2014BEJuel, title = {Investigating the Consistency and Convexity of Restricted Boltzmann Machine Learning}, author = {BE Juel} } @misc{2014BElizaldeMRavanelliKNiDBorthGFriedland, title = {Audio-Concept Features and Hidden Markov Models for Multimedia Event Detection}, author = {B Elizalde, M Ravanelli, K Ni, D Borth, G Friedland} } @misc{2014BGraham, title = {Fractional Max-Pooling}, author = {B Graham} } @misc{2014BHanBHeTSunMMaALendasse, title = {Hsr: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection}, author = {B Han, B He, T Sun, M Ma, A Lendasse} } @misc{2014BHariharanPArbelÃ¡ezRGirshickJMalik, title = {Hypercolumns for Object Segmentation and Fine-grained Localization}, author = {B Hariharan, P ArbelÃ¡ez, R Girshick, J Malik} } @misc{2014BJain, title = {Margin Perceptrons for Graphs}, author = {B Jain} } @misc{2014BJiangYSongSWeiMGWangIMcLoughlin, title = {Performance evaluation of deep bottleneck features for spoken language identification}, author = {B Jiang, Y Song, S Wei, MG Wang, I McLoughlin} } @misc{2014BKleinGLevGSadehLWolf, title = {Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation}, author = {B Klein, G Lev, G Sadeh, L Wolf} } @misc{2014BLDavisTFRodriguezAMReedJStachColorCorrectionArrangements, title = {Color Correction Arrangements For Dermoscopy}, author = {BL Davis, TF Rodriguez, AM Reed, J Stach} } @misc{2014BLDavisTFRodriguezAMReedJStachGesture-basedDermatologicData, title = {Gesture-based Dermatologic Data Collection And Presentation}, author = {BL Davis, TF Rodriguez, AM Reed, J Stach} } @misc{2014BLDavisTFRodriguezAMReedJStachMethodsAndArrangements, title = {Methods And Arrangements For Identifying Dermatological Diagnoses With Clinically Negligible Probabilties}, author = {BL Davis, TF Rodriguez, AM Reed, J Stach} } @misc{2014BLDavisTFRodriguezAMReedJStachPhysiologicAudioFingerprinting, title = {Physiologic Audio Fingerprinting}, author = {BL Davis, TF Rodriguez, AM Reed, J Stach} } @misc{2014BLengSGuoXZhangZXiong, title = {3d object retrieval with stacked local convolutional autoencoder}, author = {B Leng, S Guo, X Zhang, Z Xiong} } @misc{2014BLengXZhangMYaoZXiong, title = {A 3d model recognition mechanism based on deep boltzmann machines}, author = {B Leng, X Zhang, M Yao, Z Xiong} } @misc{2014BLiYLuCLiAGodilTSchreckMAono, title = {A comparison of 3d shape retrieval methods based on a large-scale benchmark supporting multimodal queries}, author = {B Li, Y Lu, C Li, A Godil, T Schreck, M Aono} } @misc{2014BLiuFMoJTao, title = {Speech Enhancement Based on Analysisâ€“Synthesis Framework With Improved Pitch Estimation and Spectral Envelope Enhancement}, author = {B Liu, F Mo, J Tao} } @misc{2014BLiuJLiuXBaiHLu, title = {Regularized Hierarchical Feature Learning with Non-Negative Sparsity and Selectivity for Image Classification}, author = {B Liu, J Liu, X Bai, H Lu} } @misc{2014BMettlerZKongBLiJAndersh, title = {Systems View on Spatial Planning and Perception Based on Invariants in Agent-Environment Dynamics}, author = {B Mettler, Z Kong, B Li, J Andersh} } @misc{2014BNeyshaburRTomiokaNSrebro, title = {In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning}, author = {B Neyshabur, R Tomioka, N Srebro} } @misc{2014BPooleSEDU, title = {Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods}, author = {B Poole, S EDU} } @misc{2014BShakibi, title = {Predicting parameters in deep learning}, author = {B Shakibi} } @misc{2014BShiXBaiWLiuJWang, title = {Deep Regression for Face Alignment}, author = {B Shi, X Bai, W Liu, J Wang} } @misc{2014BVandersmissenATomarFGodinWDeNeve, title = {Ghent University-iMinds at MediaEval 2014 Diverse Images: Adaptive Clustering with Deep Features}, author = {B Vandersmissen, A Tomar, F Godin, W De Neve} } @misc{2014BWang, title = {Automatic Animal Species Identification Based on Camera Trapping Data}, author = {B Wang} } @misc{2014BWichtJHennebert, title = {Camera-based Sudoku recognition with Deep Belief Network}, author = {B Wicht, J Hennebert} } @misc{2014BXieYLiuHZhangJYu, title = {Efficient image representation for object recognition via pivots selection}, author = {B Xie, Y Liu, H Zhang, J Yu} } @misc{2014BXuXWangXTang, title = {Fusing Music and Video Modalities Using Multi-timescale Shared Representations}, author = {B Xu, X Wang, X Tang} } @misc{2014BYangWYihXHeJGaoLDeng, title = {Learning Multi-Relational Semantics Using Neural-Embedding Models}, author = {B Yang, W Yih, X He, J Gao, L Deng} } @misc{2014BYanikogluYSTolgaCTirkazEFuenCaglartes, title = {Sabanci-okan system at lifeclef 2014 plant identification competition}, author = {B Yanikoglu, YS Tolga, C Tirkaz, E FuenCaglartes} } @misc{2014BÃ‡AydÄ±nEKarasakalCÄ°yigÃ¼n, title = {A Probabilistic Multiple Criteria Sorting Approach Based On Distance Functions}, author = {BÃ‡ AydÄ±n, E Karasakal, C Ä°yigÃ¼n} } @misc{2014CCChiouLCTienLTLee, title = {Effects on learning of multimedia animation combined with multidimensional concept maps}, author = {CC Chiou, LC Tien, LT Lee} } @misc{2014CCadenaJKoÅ¡eckÃ¡, title = {Semantic parsing for priming object detection in indoors Rgb-d scenes}, author = {C Cadena, J KoÅ¡eckÃ¡} } @misc{2014CClarkAStorkey, title = {Teaching Deep Convolutional Neural Networks to Play Go}, author = {C Clark, A Storkey} } @misc{2014CCreusotAMunawar, title = {Real-time Barcode Detection in the Wild}, author = {C Creusot, A Munawar} } @misc{2014CDaHZhangYSang, title = {Brain Ct Image Classification with Deep Neural Networks}, author = {C Da, H Zhang, Y Sang} } @misc{2014CDongCCLoyKHeXTang, title = {Image Super-Resolution Using Deep Convolutional Networks}, author = {C Dong, CC Loy, K He, X Tang} } @misc{2014CFinnLAHendricksTDarrell, title = {Learning Compact Convolutional Neural Networks with Nested Dropout}, author = {C Finn, LA Hendricks, T Darrell} } @misc{2014CGulcehreYBengio, title = {Adasecant: Robust Adaptive Secant Method for Stochastic Gradient}, author = {C Gulcehre, Y Bengio} } @misc{2014CHTianYWangWTMoFCHuangWSDong, title = {Pre-release sales forecasting: A model-driven context feature extraction approach}, author = {CH Tian, Y Wang, WT Mo, FC Huang, WS Dong} } @misc{2014CHungZXuSSukkarieh, title = {Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a Uav}, author = {C Hung, Z Xu, S Sukkarieh} } @misc{2014CJMaddisonAHuangISutskeverDSilver, title = {Move Evaluation In Go Using Deep Convolutional Neural Networks}, author = {CJ Maddison, A Huang, I Sutskever, D Silver} } @misc{2014CJSunSHZhuZShi, title = {Multi-View Semi-Supervised Learning Based Image Annotation}, author = {CJ Sun, SH Zhu, Z Shi} } @misc{2014CKangSLiaoYHeJWangSXiangCPan, title = {Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation}, author = {C Kang, S Liao, Y He, J Wang, S Xiang, C Pan} } @misc{2014CKoGSohnTKRemmelJMiller, title = {Hybrid Ensemble Classification of Tree Genera Using Airborne LiDAR Data}, author = {C Ko, G Sohn, TK Remmel, J Miller} } @misc{2014CLIXXIEYHUANGHWangCNIU, title = {Distributed Data Mining Based on Deep Neural Network for Wireless Sensor Network}, author = {C LI, X XIE, Y HUANG, H Wang, C NIU} } @misc{2014CLiBXuGWuSHeGTianHHao, title = {Recursive Deep Learning for Sentiment Analysis over Social Data}, author = {C Li, B Xu, G Wu, S He, G Tian, H Hao} } @misc{2014CLiuMTomizuka, title = {Control In A Safe Set: Addressing Safety In Human-robot Interactions}, author = {C Liu, M Tomizuka} } @misc{2014CLuHChenQChenHLawYXiaoCKTang, title = {1-hkust: Object Detection in Ilsvrc 2014}, author = {C Lu, H Chen, Q Chen, H Law, Y Xiao, CK Tang} } @misc{2014CMAIN, title = {Deep Neural Networks For Spoken Dialog Systems}, author = {C MAIN} } @misc{2014CMayrJPartzschMNoackSHÃ¤nzscheSScholze, title = {A Biological-Realtime Neuromorphic System in 28 nm Cmos using Low-Leakage Switched Capacitor Circuits}, author = {C Mayr, J Partzsch, M Noack, S HÃ¤nzsche, S Scholze} } @misc{2014CMitchellDCordellDFam, title = {Beginning at the End: The outcome spaces framework to guide purposive transdisciplinary research}, author = {C Mitchell, D Cordell, D Fam} } @misc{2014CNEURALRURAWSSIGNAL, title = {Trope}, author = {C NEURAL, RURAWS SIGNAL} } @misc{2014CNiNFChenBMa, title = {Multiple time-span feature fusion for deep neural network modeling}, author = {C Ni, NF Chen, B Ma} } @misc{2014CPHungDCuiYChenCLinMLevine, title = {Correlated activity supports efficient cortical processing}, author = {CP Hung, D Cui, Y Chen, C Lin, M Levine} } @misc{2014CPolancoTBuhseJACastaÃ±Ã³nGonzÃ¡lez, title = {Possible computational filter to detect proteins associated to influenza A subtype H1n1.}, author = {C Polanco, T Buhse, JA CastaÃ±Ã³n-GonzÃ¡lez} } @misc{2014CQinSSongGHuang, title = {Non-linear neighborhood component analysis based on constructive neural networks}, author = {C Qin, S Song, G Huang} } @misc{2014CSabett, title = {Estimating Tract Variables from Acoustics via Neural Networks}, author = {C Sabett} } @misc{2014CShenXHuangQZhao, title = {Learning of Proto-object Representations via Fixations on Low Resolution}, author = {C Shen, X Huang, Q Zhao} } @misc{2014CSuiRTogneriMBennamoun, title = {Extracting Deep Bottleneck Features For Visual Speech Recognition}, author = {C Sui, R Togneri, M Bennamoun} } @misc{2014CSzegedySReedDErhanDAnguelov, title = {Scalable, High-Quality Object Detection}, author = {C Szegedy, S Reed, D Erhan, D Anguelov} } @misc{2014CSzegedyWLiuYJiaPSermanetSReed, title = {Going Deeper with Convolutions}, author = {C Szegedy, W Liu, Y Jia, P Sermanet, S Reed} } @misc{2014CWDengGBHuangJXuJXTang, title = {Extreme learning machines: new trends and applications}, author = {CW Deng, GB Huang, J Xu, JX Tang} } @misc{2014CXIEYDUZGAO, title = {Restricted Boltzmann Machines with Svm for Object Recognitionâ‹†}, author = {C XIE, Y DU, Z GAO} } @misc{2014CXuSCetintasKCLeeLJLi, title = {Visual Sentiment Prediction with Deep Convolutional Neural Networks}, author = {C Xu, S Cetintas, KC Lee, LJ Li} } @misc{2014CXuYBaiJBianBGaoGWangXLiuTYLiu, title = {Rc-net: A General Framework for Incorporating Knowledge into Word Representations}, author = {C Xu, Y Bai, J Bian, B Gao, G Wang, X Liu, TY Liu} } @misc{2014CYLeeSXiePGallagherZZhangZTu, title = {Deeply-Supervised Nets}, author = {CY Lee, S Xie, P Gallagher, Z Zhang, Z Tu} } @misc{2014CYZhangCLChen, title = {An automatic setting for training restricted boltzmann machine}, author = {CY Zhang, CL Chen} } @misc{2014CZhangCShen, title = {Unsupervised Feature Learning for Dense Correspondences across Scenes}, author = {C Zhang, C Shen} } @misc{2014DARichardsPMuscarellaTBekaiiSaabLSWilfong, title = {A proteomic signature predicts response to a therapeutic vaccine in pancreas cancer; analysis from the Gi-4000-02 trial}, author = {DA Richards, P Muscarella, T Bekaii-Saab, LS Wilfong} } @misc{2014DBalduzziHVanchinathanJBuhmann, title = {Kickback cuts Backprop's red-tape: Biologically plausible credit assignment in neural networks}, author = {D Balduzzi, H Vanchinathan, J Buhmann} } @misc{2014DBollegalaTMaeharaYYoshidaKKawarabayashi, title = {Learning Word Representations from Relational Graphs}, author = {D Bollegala, T Maehara, Y Yoshida, K Kawarabayashi} } @misc{2014DCMocanuGExarchakosALiotta, title = {Deep Learning For Objective Quality Assessment Of 3d Images}, author = {DC Mocanu, G Exarchakos, A Liotta} } @misc{2014DCulibrkNSebe, title = {Temporal Dropout of Changes Approach to Convolutional Learning of Spatio-Temporal Features}, author = {D Culibrk, N Sebe} } @misc{2014DDCoxTDean, title = {Neural Networks and Neuroscience-Inspired Computer Vision}, author = {DD Cox, T Dean} } @misc{2014DEigenRFergus, title = {Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture}, author = {D Eigen, R Fergus} } @misc{2014DFanYShimARaghunathanKRoy, title = {Stt-snn: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks}, author = {D Fan, Y Shim, A Raghunathan, K Roy} } @misc{2014DGuptaRGoutamANg, title = {Multimedia Event Detection using Visual Features}, author = {D Gupta, R Goutam, A Ng} } @misc{2014DHakkaniTÃ¼rMSlaneyACelikyilmazLHeck, title = {Eye gaze for spoken language understanding in multi-modal conversational interactions}, author = {D Hakkani-TÃ¼r, M Slaney, A Celikyilmaz, L Heck} } @misc{2014DKHuASYeLLiLZhang, title = {Recognition of Facial Expression via Kernel Pca Network}, author = {DK Hu, AS Ye, L Li, L Zhang} } @misc{2014DKHuLZhangWDZhaoTYan, title = {Object Classification via PCANet and Color Constancy Model}, author = {DK Hu, L Zhang, WD Zhao, T Yan} } @misc{2014DKadetotadZXuAMohantyPYChenBLinJYe, title = {Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning}, author = {D Kadetotad, Z Xu, A Mohanty, PY Chen, B Lin, J Ye} } @misc{2014DKotziasMDenilPBlunsomNdeFreitas, title = {Deep Multi-Instance Transfer Learning}, author = {D Kotzias, M Denil, P Blunsom, N de Freitas} } @misc{2014DMenottiGChiachiaAPintoWRSchwartzHPedrini, title = {Deep Representations for Iris, Face, and Fingerprint Spoofing Attack Detection}, author = {D Menotti, G Chiachia, A Pinto, WR Schwartz, H Pedrini} } @misc{2014DMenottiGChiachiaAXFalcaoVJONeto, title = {Vehicle License Plate Recognition With Random Convolutional Networks}, author = {D Menotti, G Chiachia, AX Falcao, VJO Neto} } @misc{2014DMeryKBowyer, title = {Recognition of Facial Attributes using Adaptive Sparse Representations of Random Patches}, author = {D Mery, K Bowyer} } @misc{2014DMeyer, title = {Can Congestion in Data Center Networks Be Predicted By Of Time Of Day?}, author = {D Meyer} } @misc{2014DMeyerIntroductiontoAutoencoders, title = {Introduction to Autoencoders}, author = {D Meyer} } @misc{2014DONikelshpur, title = {Achieving Consistent Near-Optimal Pattern Recognition Accuracy Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks}, author = {DO Nikelshpur} } @misc{2014DPHelmboldPMLong, title = {On the Inductive Bias of Dropout}, author = {DP Helmbold, PM Long} } @misc{2014DPalazMMDossRCollobert, title = {Learning linearly separable features for speech recognition using convolutional neural networks}, author = {D Palaz, MM Doss, R Collobert} } @misc{2014DPalazMMagimaiDossRCollobert, title = {Joint Phoneme Segmentation Inference and Classification using CRFs}, author = {D Palaz, M Magimai-Doss, R Collobert} } @misc{2014DPalazRCollobert, title = {Raw Speech Signal-based Continuous Speech Recognition using Convolutional Neural Networks}, author = {D Palaz, R Collobert} } @misc{2014DPathakEShelhamerJLongTDarrell, title = {Fully Convolutional Multi-Class Multiple Instance Learning}, author = {D Pathak, E Shelhamer, J Long, T Darrell} } @misc{2014DQuangYChenXXie, title = {Dann: a deep learning approach for annotating the pathogenicity of genetic variants}, author = {D Quang, Y Chen, X Xie} } @misc{2014DRasmussen, title = {Hierarchical reinforcement learning in a biologically plausible neural architecture}, author = {D Rasmussen} } @misc{2014DSovilj, title = {Learning Methods for Variable Selection and Time Series Prediction}, author = {D Sovilj} } @misc{2014DStowellMDPlumbley, title = {Audio-only bird classification using unsupervised feature learning}, author = {D Stowell, MD Plumbley} } @misc{2014DTranLBourdevRFergusLTorresaniMPaluri, title = {C3d: Generic Features for Video Analysis}, author = {D Tran, L Bourdev, R Fergus, L Torresani, M Paluri} } @misc{2014DTristramKBradshaw, title = {Determining the difficulty of accelerating problems on a Gpu}, author = {D Tristram, K Bradshaw} } @misc{2014DTurcsanyABargiela, title = {Learning Local Receptive Fields in Deep Belief Networks for Visual Feature Detection}, author = {D Turcsany, A Bargiela} } @misc{2014DVRao, title = {Class Margins: Learning to (Un) Learn}, author = {DV Rao} } @misc{2014DWangXTan, title = {C-SVDDNet: An Effective Single-Layer Network for Unsupervised Feature Learning}, author = {D Wang, X Tan} } @misc{2014DWardeFarleyARabinovichDAnguelov, title = {Self-informed neural network structure learning}, author = {D Warde-Farley, A Rabinovich, D Anguelov} } @misc{2014DWuLShao, title = {Deep Dynamic Neural Networks for Gesture Segmentation and Recognition}, author = {D Wu, L Shao} } @misc{2014DXWuWPanLDXieCXHuang, title = {An Adaptive Stacked Denoising Auto-Encoder Architecture for Human Action Recognition}, author = {DX Wu, W Pan, LD Xie, CX Huang} } @misc{2014DYAmit, title = {Image Recognition Using Convolutional Neural Networks}, author = {DY Amit} } @misc{2014DYiZLeiSLiaoSZLi, title = {Learning Face Representation from Scratch}, author = {D Yi, Z Lei, S Liao, SZ Li} } @misc{2014DYiZLeiSZLi, title = {Age Estimation by Multi-scale Convolutional Network}, author = {D Yi, Z Lei, SZ Li} } @misc{2014DYuLDeng, title = {Recurrent Neural Networks and Related Models}, author = {D Yu, L Deng} } @misc{2014DYuLDengAutomaticSpeechRecognition:, title = {Automatic Speech Recognition: A Deep Learning Approach}, author = {D Yu, L Deng} } @misc{2014DYuLDengDeepNeuralNetwork-Hidden, title = {Deep Neural Network-Hidden Markov Model Hybrid Systems}, author = {D Yu, L Deng} } @misc{2014DYuLDengDeepNeuralNetworks, title = {Deep Neural Networks}, author = {D Yu, L Deng} } @misc{2014DYuLDengFeatureRepresentationLearning, title = {Feature Representation Learning in Deep Neural Networks}, author = {D Yu, L Deng} } @misc{2014DYuLDengHiddenMarkovModels, title = {Hidden Markov Models and the Variants}, author = {D Yu, L Deng} } @misc{2014DYuLDengRepresentationSharingand, title = {Representation Sharing and Transfer in Deep Neural Networks}, author = {D Yu, L Deng} } @misc{2014EBATI, title = {Deep Convolutional Neural Networks With An Application Towards Geospatial Object Recognition}, author = {E BATI} } @misc{2014EBarshanPFieguth, title = {Scalable Learning for Restricted Boltzmann Machines}, author = {E Barshan, P Fieguth} } @misc{2014EBengioYWenSRuan, title = {Handwritten Digits Classification}, author = {E Bengio, Y Wen, S Ruan} } @misc{2014ECakir, title = {Multilabel Sound Event Classification with Neural Networks}, author = {E Cakir} } @misc{2014ECovielloGLanckriet, title = {Audio-based annnotatoion of video}, author = {E Coviello, G Lanckriet} } @misc{2014EEtterEPaulson, title = {Momentum Effects on Back-Propagation Learning in a Multi-Layer Feed-Forward Neural Network}, author = {E Etter, E Paulson} } @misc{2014EHofferNAilon, title = {Deep metric learning using Triplet network}, author = {E Hoffer, N Ailon} } @misc{2014EMRehnHSprekeler, title = {Nonlinear Supervised Locality Preserving Projections for Visual Pattern Discrimination}, author = {EM Rehn, H Sprekeler} } @misc{2014EMeedsRHendriksSFarabyMBruntinkMWelling, title = {MLitB: Machine Learning in the Browser}, author = {E Meeds, R Hendriks, S Faraby, M Bruntink, M Welling} } @misc{2014EOyallonSMallat, title = {Deep Roto-Translation Scattering for Object Classification}, author = {E Oyallon, S Mallat} } @misc{2014EPanZHan, title = {Non-parametric Bayesian Learning with Deep Learning Structure and Its Applications in Wireless Networks}, author = {E Pan, Z Han} } @misc{2014ERachmawatiISSuwardiMLKhodra, title = {Survey of Local Descriptor of Object Recognition System based on Rgb-d Images}, author = {E Rachmawati, IS Suwardi, ML Khodra} } @misc{2014ETzengJHoffmanNZhangKSaenkoTDarrell, title = {Deep Domain Confusion: Maximizing for Domain Invariance}, author = {E Tzeng, J Hoffman, N Zhang, K Saenko, T Darrell} } @misc{2014FAgostinelliMHoffmanPSadowskiPBaldi, title = {Learning Activation Functions to Improve Deep Neural Networks}, author = {F Agostinelli, M Hoffman, P Sadowski, P Baldi} } @misc{2014FBarrancoCFermullerYAloimonos, title = {Contour Motion Estimation for Asynchronous Event-Driven Cameras}, author = {F Barranco, C Fermuller, Y Aloimonos} } @misc{2014FBisioSDecherchiPGastaldoRZunino, title = {Inductive Bias for Semi-supervised Extreme Learning Machine}, author = {F Bisio, S Decherchi, P Gastaldo, R Zunino} } @misc{2014FFengRLiXWang, title = {Deep Correspondence Restricted Boltzmann Machine for Cross-modal Retrieval}, author = {F Feng, R Li, X Wang} } @misc{2014FFengXWangRLi, title = {Cross-modal Retrieval with Correspondence Autoencoder}, author = {F Feng, X Wang, R Li} } @misc{2014FLiuCShenGLin, title = {Deep Convolutional Neural Fields for Depth Estimation from a Single Image}, author = {F Liu, C Shen, G Lin} } @misc{2014FSrajerAGSchwingMPollefeysTPajdla, title = {MatchBox: Indoor Image Matching via Box-like Scene Estimation}, author = {F Srajer, AG Schwing, M Pollefeys, T Pajdla} } @misc{2014FWeningerJBergmannBSchuller, title = {Introducing CURRENNTâ€“the Munich open-source Cuda RecurREnt Neural Network Toolkit}, author = {F Weninger, J Bergmann, B Schuller} } @misc{2014FZouYWangYYangKZhouYChenJSong, title = {Supervised feature learning via â„“2-norm regularized logistic regression for 3d object recognition}, author = {F Zou, Y Wang, Y Yang, K Zhou, Y Chen, J Song} } @misc{2014GAOWeixunCAOQiyingQYao, title = {Cross-Dialectal Voice Conversion with Neural Networks}, author = {GAO Weixun, CAO Qiying, Q Yao} } @misc{2014GAttardiVCozzaDSartiano, title = {Adapting Linguistic Tools for the Analysis of Italian Medical Records}, author = {G Attardi, V Cozza, D Sartiano} } @misc{2014GBRhoads, title = {Dermoscopic Data Acquisition Employing Display Illumination}, author = {GB Rhoads} } @misc{2014GBertasiusJShiLTorresani, title = {DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection}, author = {G Bertasius, J Shi, L Torresani} } @misc{2014GChen, title = {Deep Learning with Nonparametric Clustering}, author = {G Chen} } @misc{2014GChenSNSrihari, title = {A Noisy-Or Discriminative Restricted Boltzmann Machine for Recognizing Handwriting Style Development}, author = {G Chen, SN Srihari} } @misc{2014GDesjardinsHLuoACourvilleYBengio, title = {Deep Tempering}, author = {G Desjardins, H Luo, A Courville, Y Bengio} } @misc{2014GEvangelidisGSinghRHoraud, title = {Continuous gesture recognition from articulated poses}, author = {G Evangelidis, G Singh, R Horaud} } @misc{2014GKutyniokMSaundersSWrightOYilmaz, title = {Sparse Representations, Numerical Linear Algebra, and Optimization}, author = {G Kutyniok, M Saunders, S Wright, O Yilmaz} } @misc{2014GLayherFSchrodtMVButzHNeumann, title = {Adaptive learning in a compartmental model of visual cortex-how feedback enables stable category learning and refinement}, author = {G Layher, F Schrodt, MV Butz, H Neumann} } @misc{2014GMarcusAMarblestoneTDean, title = {The atoms of neural computation}, author = {G Marcus, A Marblestone, T Dean} } @misc{2014GMesnilSRifaiABordesXGlorotYBengio, title = {Unsupervised Learning of Semantics of Object Detections for Scene Categorization}, author = {G Mesnil, S Rifai, A Bordes, X Glorot, Y Bengio} } @misc{2014GMesnilYDauphinKYaoYBengioLDeng, title = {Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding}, author = {G Mesnil, Y Dauphin, K Yao, Y Bengio, L Deng} } @misc{2014GMishneRTalmonICohen, title = {Graph-Based Supervised Automatic Target Detection}, author = {G Mishne, R Talmon, I Cohen} } @misc{2014GMontufar, title = {Deep Narrow Boltzmann Machines are Universal Approximators}, author = {G Montufar} } @misc{2014GMontÃºfarRPascanuKChoYBengio, title = {Supplementary Material: On the Number of Linear Regions of Deep Neural Networks}, author = {G MontÃºfar, R Pascanu, K Cho, Y Bengio} } @misc{2014GPapandreouIKokkinosPASavalle, title = {Untangling Local and Global Deformations in Deep Convolutional Networks for Image Classification and Sliding Window Detection}, author = {G Papandreou, I Kokkinos, PA Savalle} } @misc{2014GRieglerDFerstlMRÃ¼therHBischof, title = {Hough Networks for Head Pose Estimation and Facial Feature Localization}, author = {G Riegler, D Ferstl, M RÃ¼ther, H Bischof} } @misc{2014GVHahnPowellDArchangeli, title = {Testing AutoTrace: A machine-learning approach to automated tongue contour data extraction}, author = {GV Hahn-Powell, D Archangeli} } @misc{2014GZhongMCheriet, title = {Low Rank Tensor Manifold Learning}, author = {G Zhong, M Cheriet} } @misc{2014HAjakanPGermainHLarochelleFLaviolette, title = {Domain-Adversarial Neural Networks}, author = {H Ajakan, P Germain, H Larochelle, F Laviolette} } @misc{2014HAliSNTranASAGarcezTWeyde, title = {Convolutional Data: Towards Deep Audio Learning from Big Data}, author = {H Ali, SN Tran, ASA Garcez, T Weyde} } @misc{2014HBKazemianSAhmed, title = {Comparisons of machine learning techniques for detecting malicious webpages}, author = {HB Kazemian, S Ahmed} } @misc{2014HChoiHPark, title = {A hierarchical structure for gesture recognition using Rgb-d sensor}, author = {H Choi, H Park} } @misc{2014HFGolinoCMAGomesDAndrade, title = {Predicting Academic Achievement of High-School Students Using Machine Learning}, author = {HF Golino, CMA Gomes, D Andrade} } @misc{2014HFanMYangZCaoYJiangQYin, title = {Learning Compact Face Representation: Packing a Face into an int32}, author = {H Fan, M Yang, Z Cao, Y Jiang, Q Yin} } @misc{2014HFangCHu, title = {Recognizing human activity in smart home using deep learning algorithm}, author = {H Fang, C Hu} } @misc{2014HFangSGuptaFIandolaRSrivastavaLDeng, title = {From Captions to Visual Concepts and Back}, author = {H Fang, S Gupta, F Iandola, R Srivastava, L Deng} } @misc{2014HHamooniAMueen, title = {Dual-domain Hierarchical Classification of Phonetic Time Series}, author = {H Hamooni, A Mueen} } @misc{2014HKagayaKAizawaMOgawa, title = {Food Detection and Recognition Using Convolutional Neural Network}, author = {H Kagaya, K Aizawa, M Ogawa} } @misc{2014HKamyshanskaRMemisevic, title = {The Potential Energy of an Autoencoder}, author = {H Kamyshanska, R Memisevic} } @misc{2014HLiRZhaoXWang, title = {Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification}, author = {H Li, R Zhao, X Wang} } @misc{2014HLiuBMaLQinJPangCZhangQHuang, title = {Set-label modeling and deep metric learning on person re-identification}, author = {H Liu, B Ma, L Qin, J Pang, C Zhang, Q Huang} } @misc{2014HLvGYuXTianGWu, title = {Deep learning-based target customer position extraction on social network}, author = {H Lv, G Yu, X Tian, G Wu} } @misc{2014HMobahiJWFisherIII, title = {On the Link Between Gaussian Homotopy Continuation and Convex Envelopes}, author = {H Mobahi, JW Fisher III} } @misc{2014HMobahiJWFisherIIICoarse-to-FineMinimizationof, title = {Coarse-to-Fine Minimization of Some Common Nonconvexities}, author = {H Mobahi, JW Fisher III} } @misc{2014HPMartÃnezGNYannakakis, title = {Deep Multimodal Fusion: Combining Discrete Events and Continuous Signals}, author = {HP MartÃnez, GN Yannakakis} } @misc{2014HPanSIOlsenYZhu, title = {Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection}, author = {H Pan, SI Olsen, Y Zhu} } @misc{2014HQiaoXXiYLiWWuFLi, title = {Biologically Inspired Visual Model With Preliminary Cognition and Active Attention Adjustment}, author = {H Qiao, X Xi, Y Li, W Wu, F Li} } @misc{2014HQuXXieYLiuMZhangLLu, title = {Improved Perception-Based Spiking Neuron Learning Rule for Real-Time User Authentication}, author = {H Qu, X Xie, Y Liu, M Zhang, L Lu} } @misc{2014HSchulzKChoTRaikoSBehnke, title = {Two-layer contractive encodings for learning stable nonlinear features}, author = {H Schulz, K Cho, T Raiko, S Behnke} } @misc{2014HSedghiAAnandkumar, title = {Provable Methods for Training Neural Networks with Sparse Connectivity}, author = {H Sedghi, A Anandkumar} } @misc{2014HSu, title = {Nuclei/Cell Detection in Microscopic Skeletal Muscle Fiber Images and Histopathological Brain Tumor Images Using Sparse Optimizations}, author = {H Su} } @misc{2014HTYuFRen, title = {Tuta1 at the Ntcir-11 IMine Task}, author = {HT Yu, F Ren} } @misc{2014HTosun, title = {Atomic Energy Models For Machine Learning: Atomic Restricted Boltzmann Machines}, author = {H Tosun} } @misc{2014HVKoops, title = {A Deep Neural Network Approach to Automatic Birdsong Recognition}, author = {HV Koops} } @misc{2014HValpola, title = {From neural Pca to deep unsupervised learning}, author = {H Valpola} } @misc{2014HWang, title = {Introduction to Word2vec and its application to find predominant word senses}, author = {H Wang} } @misc{2014HWangClassifyingGray-scaleSar, title = {Classifying Gray-scale Sar Images: Adeep Learning Approach}, author = {H Wang} } @misc{2014HWangNWangDYYeung, title = {Collaborative Deep Learning for Recommender Systems}, author = {H Wang, N Wang, DY Yeung} } @misc{2014HWangXShiDYYeung, title = {Relational Stacked Denoising Autoencoder for Tag Recommendation}, author = {H Wang, X Shi, DY Yeung} } @misc{2014HWangYZhaoYXuXXuXSuoQJi, title = {Cross-language speech attribute detection and phone recognition for Tibetan using deep learning}, author = {H Wang, Y Zhao, Y Xu, X Xu, X Suo, Q Ji} } @misc{2014HYanJLuXZhou, title = {Prototype-Based Discriminative Feature Learning for Kinship Verification}, author = {H Yan, J Lu, X Zhou} } @misc{2014HYangIPatras, title = {Privileged Information-based Conditional Structured Output Regression Forest for Facial Point Detection}, author = {H Yang, I Patras} } @misc{2014HYinXJiaoYChaiBFang, title = {Scene Classification Based on Single-layer Sae and Svm}, author = {H Yin, X Jiao, Y Chai, B Fang} } @misc{2014HZhaoJLuoZHuangTNagumoJMurayama, title = {Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding}, author = {H Zhao, J Luo, Z Huang, T Nagumo, J Murayama} } @misc{2014HZhaoPPoupartYZhangMLysy, title = {SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering}, author = {H Zhao, P Poupart, Y Zhang, M Lysy} } @misc{2014HZhouGBHuangZLinHWangYCSoh, title = {Stacked Extreme Learning Machines}, author = {H Zhou, GB Huang, Z Lin, H Wang, YC Soh} } @misc{2014HZhouJTangHZheng, title = {Machine Learning for Medical Applications}, author = {H Zhou, J Tang, H Zheng} } @misc{2014IChungTNSainathBRamabhadranMPicheny, title = {Parallel deep neural network training for big data on blue gene/Q}, author = {I Chung, TN Sainath, B Ramabhadran, M Picheny} } @misc{2014ICortesCirianoQulAinVSubramanianBLenselink, title = {Polypharmacology Modelling Using Proteochemometrics (pcm): Recent Methodological Developments, Applications to Target Families, and Future Prospects}, author = {I Cortes-Ciriano, Q ul Ain, V Subramanian, B Lenselink} } @misc{2014IHJhuoDTLee, title = {Video Event Detection via Multi-modality Deep Learning}, author = {IH Jhuo, DT Lee} } @misc{2014IJGoodfellowJPougetAbadieMMirzaBXu, title = {Generative Adversarial Nets}, author = {IJ Goodfellow, J Pouget-Abadie, M Mirza, B Xu} } @misc{2014IJKimXXie, title = {Handwritten Hangul recognition using deep convolutional neural networks}, author = {IJ Kim, X Xie} } @misc{2014INwoguYZhou, title = {Shared features for multiple face-based biometrics}, author = {I Nwogu, Y Zhou} } @misc{2014ISutskeverOVinyalsQVLe, title = {Sequence to Sequence Learning with Neural Networks}, author = {I Sutskever, O Vinyals, QV Le} } @misc{2014ITitovEKhoddam, title = {Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework}, author = {I Titov, E Khoddam} } @misc{2014ITseyzer, title = {An Optimization of Deep Neural Networks in Asr using Singular Value Decomposition}, author = {I Tseyzer} } @misc{2014JASÃ¡nchezVRomeroAHToselliEVidal, title = {Icfhr2014 Competition on Handwritten Text Recognition on tranScriptorium Datasets (HTRtS)}, author = {JA SÃ¡nchez, V Romero, AH Toselli, E Vidal} } @misc{2014JAVanegasJArevaloSOtÃ¡loraFPÃ¡ez, title = {MindLab at ImageCLEF 2014: Scalable Concept Image Annotation}, author = {JA Vanegas, J Arevalo, S OtÃ¡lora, F PÃ¡ez} } @misc{2014JBergstraBKomerCEliasmithDWardeFarley, title = {Preliminary evaluation of hyperopt algorithms on HPOLib}, author = {J Bergstra, B Komer, C Eliasmith, D Warde-Farley} } @misc{2014JBohannon, title = {Helping robots see the big picture}, author = {J Bohannon} } @misc{2014JCBanCHChang, title = {The Spatial Complexity of Inhomogeneous Multi-layer Neural Networks}, author = {JC Ban, CH Chang} } @misc{2014JCarreiraAKarSTulsianiJMalik, title = {Virtual View Networks for Object Reconstruction}, author = {J Carreira, A Kar, S Tulsiani, J Malik} } @misc{2014JCarreiraRCaseiroJBatistaCSminchisescu, title = {Free-Form Region Description with Second-Order Pooling}, author = {J Carreira, R Caseiro, J Batista, C Sminchisescu} } @misc{2014JChengDKartsaklisEGrefenstette, title = {Investigating the Role of Prior Disambiguation in Deep-learning Compositional Models of Meaning}, author = {J Cheng, D Kartsaklis, E Grefenstette} } @misc{2014JChorowskiDBahdanauKChoYBengio, title = {End-to-end Continuous Speech Recognition using Attention-based Recurrent Nn: First Results}, author = {J Chorowski, D Bahdanau, K Cho, Y Bengio} } @misc{2014JChungCGulcehreKHChoYBengio, title = {Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling}, author = {J Chung, C Gulcehre, KH Cho, Y Bengio} } @misc{2014JCummer, title = {Methodology and Techniques for Building Modular Brain-Computer Interfaces}, author = {J Cummer} } @misc{2014JDaiYNWu, title = {Generative Modeling of Convolutional Neural Networks}, author = {J Dai, YN Wu} } @misc{2014JDonahueLAHendricksSGuadarramaMRohrbach, title = {Long-term Recurrent Convolutional Networks for Visual Recognition and Description}, author = {J Donahue, LA Hendricks, S Guadarrama, M Rohrbach} } @misc{2014JDongSSoatto, title = {Domain-Size Pooling in Local Descriptors: Dsp-sift}, author = {J Dong, S Soatto} } @misc{2014JDoshiCMasonAWagnerZKira, title = {Deep Segments: Comparisons between Scenes and their Constituent Fragments using Deep Learning}, author = {J Doshi, C Mason, A Wagner, Z Kira} } @misc{2014JDu, title = {Irrelevant Variability Normalization via Hierarchical Deep Neural Networks for Online Handwritten Chinese Character Recognition}, author = {J Du} } @misc{2014JDuJSHuBZhuSWeiLRDai, title = {A Study of Designing Compact Classifiers using Deep Neural Networks for Online Handwritten Chinese Character Recognition}, author = {J Du, JS Hu, B Zhu, S Wei, LR Dai} } @misc{2014JEdwards, title = {Signal Processing in Next-Generation Prosthetics [Special Reports]}, author = {J Edwards} } @misc{2014JGADolfingKMGroetheRSDixonJRBellegarda, title = {Multi-script Handwriting Recognition Using A Universal Recognizer}, author = {JGA Dolfing, KM Groethe, RS Dixon, JR Bellegarda} } @misc{2014JGDolfingJRBellegardaUMeierRDixon, title = {Real-time Stroke-order And Stroke-direction Independent Handwriting Recognition}, author = {JG Dolfing, JR Bellegarda, U Meier, R Dixon} } @misc{2014JGlass, title = {Non-negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition}, author = {J Glass} } @misc{2014JHanDZhangXHuLGuoJRenFWu, title = {Background Prior Based Salient Object Detection via Deep Reconstruction Residual}, author = {J Han, D Zhang, X Hu, L Guo, J Ren, F Wu} } @misc{2014JHelmsen, title = {Systems and methods for analyzing data using deep belief networks (dbn) and identifying a pattern in a graph}, author = {J Helmsen} } @misc{2014JHoffmanDPathakTDarrellKSaenko, title = {Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning}, author = {J Hoffman, D Pathak, T Darrell, K Saenko} } @misc{2014JHuangWXiaSYan, title = {Deep Search with Attribute-aware Deep Network}, author = {J Huang, W Xia, S Yan} } @misc{2014JJiangRHuLMikelYDou, title = {Accuracy evaluation of deep belief networks with fixed-point arithmetic}, author = {J Jiang, R Hu, L Mikel, Y Dou} } @misc{2014JJinADundarECulurciello, title = {Flattened Convolutional Neural Networks for Feedforward Acceleration}, author = {J Jin, A Dundar, E Culurciello} } @misc{2014JJinVGokhaleADundarBKrishnamurthyBMartini, title = {An Efficient Implementation of Deep Convolutional Neural Networks on a Mobile Coprocessor}, author = {J Jin, V Gokhale, A Dundar, B Krishnamurthy, B Martini} } @misc{2014JKChenZChenZChiHFu, title = {Emotion Recognition in the Wild with Feature Fusion and Multiple Kernel Learning}, author = {JK Chen, Z Chen, Z Chi, H Fu} } @misc{2014JLedererSGuadarrama, title = {Compute Less to Get More: Using Orc to Improve Sparse Filtering}, author = {J Lederer, S Guadarrama} } @misc{2014JLehmanJCluneSRisi, title = {An Anarchy of Methods: Current Trends in How Intelligence Is Abstracted in Ai}, author = {J Lehman, J Clune, S Risi} } @misc{2014JLi, title = {Feature Weight Tuning for Recursive Neural Networks}, author = {J Li} } @misc{2014JLiHChangJYang, title = {Sparse Deep Stacking Network for Image Classification}, author = {J Li, H Chang, J Yang} } @misc{2014JLiZStruzikLZhangACichocki, title = {Feature Learning from Incomplete Eeg with Denoising Autoencoder}, author = {J Li, Z Struzik, L Zhang, A Cichocki} } @misc{2014JLiuMGongJZhaoHLiLJiao, title = {Difference representation learning using stacked restricted Boltzmann machines for change detection in Sar images}, author = {J Liu, M Gong, J Zhao, H Li, L Jiao} } @misc{2014JLongEShelhamerTDarrell, title = {Fully Convolutional Networks for Semantic Segmentation}, author = {J Long, E Shelhamer, T Darrell} } @misc{2014JLyonsADehzangiRHeffernanASharma, title = {Predicting backbone CÎ± angles and dihedrals from protein sequences by stacked sparse autoâ€encoder deep neural network}, author = {J Lyons, A Dehzangi, R Heffernan, A Sharma} } @misc{2014JMBae, title = {Clinical Decision Analysis using Decision Tree}, author = {JM Bae} } @misc{2014JMTomczakMZiÄ™ba, title = {Classification Restricted Boltzmann Machine for comprehensible credit scoring model}, author = {JM Tomczak, M ZiÄ™ba} } @misc{2014JMacÃ¡kODrbohlav, title = {A Simple Stochastic Algorithm for Structural Features Learning}, author = {J MacÃ¡k, O Drbohlav} } @misc{2014JMairalFBachJPonce, title = {Foundations and TrendsÂ® in Computer Graphics and Vision}, author = {J Mairal, F Bach, J Ponce} } @misc{2014JMaoWXuYYangJWangALYuille, title = {Explain Images with Multimodal Recurrent Neural Networks}, author = {J Mao, W Xu, Y Yang, J Wang, AL Yuille} } @misc{2014JMartinezHHHoosJJLittle, title = {Stacked Quantizers for Compositional Vector Compression}, author = {J Martinez, HH Hoos, JJ Little} } @misc{2014JNiuYQianKYu, title = {Acoustic emotion recognition using deep neural network}, author = {J Niu, Y Qian, K Yu} } @misc{2014JRSmith, title = {Semantics of Visual Discrimination}, author = {JR Smith} } @misc{2014JRedmonAAngelova, title = {Real-Time Grasp Detection Using Convolutional Neural Networks}, author = {J Redmon, A Angelova} } @misc{2014JRudyWDingDJImGWTaylor, title = {Neural Network Regularization via Robust Weight Factorization}, author = {J Rudy, W Ding, DJ Im, GW Taylor} } @misc{2014JShenMLee, title = {Implementation of discriminative and generative deep learning}, author = {J Shen, M Lee} } @misc{2014JTHLoYGuiYPeng, title = {The normalized risk-averting error criterion for avoiding nonglobal local minima in training neural networks}, author = {JTH Lo, Y Gui, Y Peng} } @misc{2014JTSpringenbergADosovitskiyTBroxMRiedmiller, title = {Striving for Simplicity: The All Convolutional Net}, author = {JT Springenberg, A Dosovitskiy, T Brox, M Riedmiller} } @misc{2014JTompsonMSteinYLecunKPerlin, title = {Real-time continuous pose recovery of human hands using convolutional networks}, author = {J Tompson, M Stein, Y Lecun, K Perlin} } @misc{2014JTompsonRGoroshinAJainYLeCunCBregler, title = {Efficient Object Localization Using Convolutional Networks}, author = {J Tompson, R Goroshin, A Jain, Y LeCun, C Bregler} } @misc{2014JWanDWangSCHHoiPWuJZhuYZhangJLi, title = {Deep Learning for Content-Based Image Retrieval: A Comprehensive Study}, author = {J Wan, D Wang, SCH Hoi, P Wu, J Zhu, Y Zhang, J Li} } @misc{2014JWangCKangYHeSXiangCPan, title = {Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge}, author = {J Wang, C Kang, Y He, S Xiang, C Pan} } @misc{2014JWangZDengSWangQGao, title = {Training Generalized Feedforword Kernelized Neural Networks on Very Large Datasets for Regression Using Minimal-Enclosing-Ball Approximation}, author = {J Wang, Z Deng, S Wang, Q Gao} } @misc{2014JXuHLiSZhou, title = {An Overview of Deep Generative Models}, author = {J Xu, H Li, S Zhou} } @misc{2014JYYu, title = {Design of Distributed Recommendation Engine Based on Hadoop and Mahout}, author = {JY Yu} } @misc{2014JYangYSunLZhangQZhang, title = {Robust Multi-Layer Hierarchical Model for Digit Character Recognition}, author = {J Yang, Y Sun, L Zhang, Q Zhang} } @misc{2014JYosinskiJCluneYBengioHLipson, title = {How transferable are features in deep neural networks?}, author = {J Yosinski, J Clune, Y Bengio, H Lipson} } @misc{2014JZhangMKanSShanXZhaoXChen, title = {Topic-aware Deep Auto-encoders (tda) for Face Alignment}, author = {J Zhang, M Kan, S Shan, X Zhao, X Chen} } @misc{2014KAddankiDWu, title = {Transduction Recursive Auto-Associative Memory: Learning Bilingual Compositional Distributed Vector Representations of Inversion Transduction Grammars}, author = {K Addanki, D Wu} } @misc{2014KBISWARANJANSSARKARDRASETHI, title = {Diagnosis Of Diabetic Retinopathy By Segmentation Of Blood Vessels In Retinal Images}, author = {K BISWARANJAN, S SARKAR, DRA SETHI} } @misc{2014KBRajaRRaghavendraVKVemuriCBusch, title = {Smartphone based visible iris recognition using deep sparse filtering}, author = {KB Raja, R Raghavendra, VK Vemuri, C Busch} } @misc{2014KChalupkaPPeronaFEberhardt, title = {Visual Causal Feature Learning}, author = {K Chalupka, P Perona, F Eberhardt} } @misc{2014KChangCChen, title = {A Learning Framework for Age Rank Estimation based on Face Images with Scattering Transform}, author = {K Chang, C Chen} } @misc{2014KDuh, title = {Deep Learning for Natural Language Processing and Machine Translation}, author = {K Duh} } @misc{2014KEggenspergerFHutterHHHoosKLeytonBrown, title = {Efficient Benchmarking of Hyperparameter Optimizers via Surrogates}, author = {K Eggensperger, F Hutter, HH Hoos, K Leyton-Brown} } @misc{2014KFragkiadakiPArbelaezPFelsenJMalik, title = {Spatio-Temporal Moving Object Proposals}, author = {K Fragkiadaki, P Arbelaez, P Felsen, J Malik} } @misc{2014KGoelRVohra, title = {Learning Temporal Dependencies in Data Using a Dbn-blstm}, author = {K Goel, R Vohra} } @misc{2014KHan, title = {Supervised Speech Separation And Processing}, author = {K Han} } @misc{2014KHanDWang, title = {Neural Network Based Pitch Tracking In Very Noisy Speech}, author = {K Han, D Wang} } @misc{2014KHeJSun, title = {Convolutional Neural Networks at Constrained Time Cost}, author = {K He, J Sun} } @misc{2014KHwangWSung, title = {Fixed-point feedforward deep neural network design using weights+ 1, 0, andâˆ’ 1}, author = {K Hwang, W Sung} } @misc{2014KINTEKNG, title = {A Distributed Implementation of Training the Restricted Boltzmann Machine}, author = {KINTEK NG} } @misc{2014KKangXWang, title = {Fully Convolutional Neural Networks for Crowd Segmentation}, author = {K Kang, X Wang} } @misc{2014KKim, title = {Emotion Modeling and Machine Learning in Affective Computing}, author = {K Kim} } @misc{2014KLencAVedaldi, title = {Understanding image representations by measuring their equivariance and equivalence}, author = {K Lenc, A Vedaldi} } @misc{2014KNodaYYamaguchiKNakadaiHGOkunoTOgata, title = {Audio-visual speech recognition using deep learning}, author = {K Noda, Y Yamaguchi, K Nakadai, HG Okuno, T Ogata} } @misc{2014KRohanimanesh, title = {An Information Theoretic Approach to Quantifying Text Interestingness}, author = {K Rohanimanesh} } @misc{2014KSTaiSXu, title = {Distributed Training of Neural Network Language Models}, author = {KS Tai, S Xu} } @misc{2014KTengJWangMXuHLu, title = {Mask Assisted Object Coding with Deep Learning for Object Retrieval in Surveillance Videos}, author = {K Teng, J Wang, M Xu, H Lu} } @misc{2014LAvdiyenkoNBertschingerJJost, title = {Adaptive Information-Theoretical Feature Selection for Pattern Classification}, author = {L Avdiyenko, N Bertschinger, J Jost} } @misc{2014LBadinoADAusilioLFadigaGMetta, title = {Computational modeling and validation of the motor contribution to speech perception}, author = {L Badino, AD Ausilio, L Fadiga, G Metta} } @misc{2014LBazzaniABergamoDAnguelovLTorresani, title = {Self-Taught Object Localization with Deep Networks}, author = {L Bazzani, A Bergamo, D Anguelov, L Torresani} } @misc{2014LBrunGPercannellaASaggeseMVento, title = {HAck: A system for the recognition of human actions by kernels of visual strings}, author = {L Brun, G Percannella, A Saggese, M Vento} } @misc{2014LCChenGPapandreouIKokkinosKMurphy, title = {Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs}, author = {LC Chen, G Papandreou, I Kokkinos, K Murphy} } @misc{2014LCaoCWang, title = {Practice in Synonym Extraction at Large Scale}, author = {L Cao, C Wang} } @misc{2014LChaoJTaoMYangYLi, title = {Improving generation performance of speech emotion recognition by denoising autoencoders}, author = {L Chao, J Tao, M Yang, Y Li} } @misc{2014LChaoJTaoMYangYLiZWen, title = {Multi-scale Temporal Modeling for Dimensional Emotion Recognition in Video}, author = {L Chao, J Tao, M Yang, Y Li, Z Wen} } @misc{2014LChenSZhuZLiJHu, title = {Image classification via learning dissimilarity measure in non-euclidean spaces}, author = {L Chen, S Zhu, Z Li, J Hu} } @misc{2014LDengXHeGTurDHakkanitur, title = {Kernel Deep Convex Networks And End-to-end Learning}, author = {L Deng, X He, G Tur, D Hakkani-tur} } @misc{2014LDenoyerPGallinari, title = {Deep Sequential Neural Network}, author = {L Denoyer, P Gallinari} } @misc{2014LDinhDKruegerYBengio, title = {Nice: Non-linear Independent Components Estimation}, author = {L Dinh, D Krueger, Y Bengio} } @misc{2014LGHafemann, title = {An analysis of deep neural networks for texture classification}, author = {LG Hafemann} } @misc{2014LGuoSLiXNiuYDou, title = {A Study on Layer Connection Strategies in Stacked Convolutional Deep Belief Networks}, author = {L Guo, S Li, X Niu, Y Dou} } @misc{2014LHChenZHLingLJLiuLRDai, title = {Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training}, author = {LH Chen, ZH Ling, LJ Liu, LR Dai} } @misc{2014LLMaJWu, title = {A Tibetan Component Representation Learning Method for Online Handwritten Tibetan Character Recognition}, author = {LL Ma, J Wu} } @misc{2014LLiuJHuSZhangWDeng, title = {Extended Supervised Descent Method for Robust Face Alignment}, author = {L Liu, J Hu, S Zhang, W Deng} } @misc{2014LMouGLiZJinLZhangTWang, title = {Tbcnn: A Tree-Based Convolutional Neural Network for Programming Language Processing}, author = {L Mou, G Li, Z Jin, L Zhang, T Wang} } @misc{2014LNieSZKumar, title = {Periocular Recognition using Unsupervised Convolutional Rbm Feature Learning}, author = {L Nie, SZ Kumar} } @misc{2014LPeiMYeXZhaoTXiangTLi, title = {Learning spatio-temporal features for action recognition from the side of the video}, author = {L Pei, M Ye, X Zhao, T Xiang, T Li} } @misc{2014LShenGSunSWangEWuQHuang, title = {Sharing Model With Multi-level Feature Representations}, author = {L Shen, G Sun, S Wang, E Wu, Q Huang} } @misc{2014LXuJSJRenCLiuJJia, title = {Deep Convolutional Neural Network for Image Deconvolution}, author = {L Xu, JSJ Ren, C Liu, J Jia} } @misc{2014LXueFSu, title = {Auditory Scene Classification with Deep Belief Network}, author = {L Xue, F Su} } @misc{2014LYeMZhuSXiaHPan, title = {Cascaded Convolutional Neural Network for Eye Detection Under Complex Scenarios}, author = {L Ye, M Zhu, S Xia, H Pan} } @misc{2014LYuKMHermannPBlunsomSPulman, title = {Deep Learning for Answer Sentence Selection}, author = {L Yu, KM Hermann, P Blunsom, S Pulman} } @misc{2014LZhangTYangRJinZHZhou, title = {Online Bandit Learning for a Special Class of Non-convex Losses}, author = {L Zhang, T Yang, R Jin, ZH Zhou} } @misc{2014LZhangYFNieZHWang, title = {Image De-Noising Using Deep Learning}, author = {L Zhang, YF Nie, ZH Wang} } @misc{2014LZhaoKJia, title = {Deep Adaptive Log-Demonsâ€“Diffeomorphic Image Registration with Very Large Deformations}, author = {L Zhao, K Jia} } @misc{2014LZhengSWangPGuoHLiangQTian, title = {Tensor index for large scale image retrieval}, author = {L Zheng, S Wang, P Guo, H Liang, Q Tian} } @misc{2014LZhongQLiuPYangJHuangDNMetaxas, title = {Learning Multiscale Active Facial Patches for Expression Analysis}, author = {L Zhong, Q Liu, P Yang, J Huang, DN Metaxas} } @misc{2014MAARashwanAAAlSallabHMRaafatARafea, title = {Automatic Arabic diacritics restoration based on deep nets}, author = {MAA Rashwan, AA Al Sallab, HM Raafat, A Rafea} } @misc{2014MAKeyvanradMMHomayounpour, title = {Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy}, author = {MA Keyvanrad, MM Homayounpour} } @misc{2014MBhattacharyyaSBandyopadhyay, title = {Finding quasi core with simulated stacked neural networks}, author = {M Bhattacharyya, S Bandyopadhyay} } @misc{2014MBlaschko, title = {Advances in Empirical Risk Minimization for Image Analysis and Pattern Recognition}, author = {M Blaschko} } @misc{2014MBuccoliPBestaginiMZanoniASartiSTubaro, title = {Unsupervised Feature Learning For Bootleg Detection Using Deep Learning Architectures}, author = {M Buccoli, P Bestagini, M Zanoni, A Sarti, S Tubaro} } @misc{2014MCimpoiSMajiAVedaldi, title = {Deep convolutional filter banks for texture recognition and segmentation}, author = {M Cimpoi, S Maji, A Vedaldi} } @misc{2014MCogswellXLinSPurushwalkamDBatra, title = {Combining the Best of Graphical Models and ConvNets for Semantic Segmentation}, author = {M Cogswell, X Lin, S Purushwalkam, D Batra} } @misc{2014MCourbariauxYBengioJPDavid, title = {Low precision arithmetic for deep learning}, author = {M Courbariaux, Y Bengio, JP David} } @misc{2014MDCollinsPKohli, title = {Memory Bounded Deep Convolutional Networks}, author = {MD Collins, P Kohli} } @misc{2014MDMcDonnellMDTisseraAvanSchaikJTapson, title = {Fast, simple and accurate handwritten digit classification using extreme learning machines with shaped input-weights}, author = {MD McDonnell, MD Tissera, A van Schaik, J Tapson} } @misc{2014MEMidhunSRNairVTPrabhakarSSKumar, title = {Deep Model for Classification of Hyperspectral image using Restricted Boltzmann Machine}, author = {ME Midhun, SR Nair, VT Prabhakar, SS Kumar} } @misc{2014MGhifaryWBKleijnMZhang, title = {Domain Adaptive Neural Networks for Object Recognition}, author = {M Ghifary, WB Kleijn, M Zhang} } @misc{2014MGieringKReddyVVenugopalan, title = {Multi-modal Sensor Registration for Vehicle Perception via Deep Neural Networks}, author = {M Giering, K Reddy, V Venugopalan} } @misc{2014MHarandiMSalzmann, title = {Riemannian Coding and Dictionary Learning: Kernels to the Rescue}, author = {M Harandi, M Salzmann} } @misc{2014MJSkwarkDRaimondiMMichelAElofsson, title = {Improved contact predictions using the recognition of protein like contact patterns.}, author = {MJ Skwark, D Raimondi, M Michel, A Elofsson} } @misc{2014MJWitteveen, title = {Identification and Elucidation of Expression Quantitative Trait Loci (eQTL) and their regulating mechanisms using Decodive Deep Learning}, author = {MJ Witteveen} } @misc{2014MJaderbergKSimonyanAVedaldiAZisserman, title = {Reading Text in the Wild with Convolutional Neural Networks}, author = {M Jaderberg, K Simonyan, A Vedaldi, A Zisserman} } @misc{2014MJaderbergKSimonyanAVedaldiAZissermanDeepStructuredOutput, title = {Deep Structured Output Learning for Unconstrained Text Recognition}, author = {M Jaderberg, K Simonyan, A Vedaldi, A Zisserman} } @misc{2014MJanzaminHSedghiAAnandkumar, title = {Matrix and Tensor Features for Discriminative Learning}, author = {M Janzamin, H Sedghi, A Anandkumar} } @misc{2014MJanzaminHSedghiAAnandkumarScoreFunctionFeatures, title = {Score Function Features for Discriminative Learning}, author = {M Janzamin, H Sedghi, A Anandkumar} } @misc{2014MJungJHwangJTani, title = {Multiple Spatio-Temporal Scales Neural Network for Contextual Visual Recognition of Human Actions}, author = {M Jung, J Hwang, J Tani} } @misc{2014MKarthickSUmesh, title = {Improving Deep Neural Networks Using State Projection Vectors Of Subspace Gaussian Mixture Model As Features}, author = {M Karthick, S Umesh} } @misc{2014MKhalilHaniLSSung, title = {A convolutional neural network approach for face verification}, author = {M Khalil-Hani, LS Sung} } @misc{2014MKiefelVJampaniPVGehler, title = {Permutohedral Lattice CNNs}, author = {M Kiefel, V Jampani, PV Gehler} } @misc{2014MKim, title = {Greedy Approaches to Semi-Supervised Subspace Learning}, author = {M Kim} } @misc{2014MKleÄ‡DKorÅ¾inek, title = {Unsupervised Feature Pre-training of the Scattering Wavelet Transform for Musical Genre Recognition}, author = {M KleÄ‡, D KorÅ¾inek} } @misc{2014MKorpusikNSchmidtJDrexlerSCyphersJGlass, title = {Data collection and language understanding of food descriptions}, author = {M Korpusik, N Schmidt, J Drexler, S Cyphers, J Glass} } @misc{2014MKoutsombogeraHPapageorgiou, title = {Multimodal Analytics and its Data Ecosystem}, author = {M Koutsombogera, H Papageorgiou} } @misc{2014MKÃ¤cheleDZharkovSMeudtFSchwenker, title = {Prosodic, spectral and voice quality feature selection using a long-term stopping criterion for audio-based emotion recognition}, author = {M KÃ¤chele, D Zharkov, S Meudt, F Schwenker} } @misc{2014MKÃ¤cheleMGlodekDZharkovSMeudt, title = {Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression}, author = {M KÃ¤chele, M Glodek, D Zharkov, S Meudt} } @misc{2014MLeordeanuARaduRSukthankar, title = {Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering}, author = {M Leordeanu, A Radu, R Sukthankar} } @misc{2014MLiDGAndersenJWParkAJSmolaAAhmed, title = {Scaling Distributed Machine Learning with the Parameter Server}, author = {M Li, DG Andersen, JW Park, AJ Smola, A Ahmed} } @misc{2014MLiangZLiTChenJZeng, title = {Integrative Data Analysis of Multi-platform Cancer Data with a Multimodal Deep Learning Approach}, author = {M Liang, Z Li, T Chen, J Zeng} } @misc{2014MLinSLiXLuoSYan, title = {Purine: A bi-graph based deep learning framework}, author = {M Lin, S Li, X Luo, S Yan} } @misc{2014MLÃ¤ngkvistALoutfi, title = {Learning Feature Representations with a Cost-Relevant Sparse Autoencoder}, author = {M LÃ¤ngkvist, A Loutfi} } @misc{2014MMalinowskiMFritz, title = {Towards a Visual Turing Challenge}, author = {M Malinowski, M Fritz} } @misc{2014MMirzaSOsindero, title = {Conditional Generative Adversarial Nets}, author = {M Mirza, S Osindero} } @misc{2014MOginoTShibaharaYNoguchiTTsujita, title = {High-definition 3d Image Processing Technology for Ultrasound Diagnostic Scanners}, author = {M Ogino, T Shibahara, Y Noguchi, T Tsujita} } @misc{2014MPesekALeonardisMMarolt, title = {A compositional hierarchical model for music information retrieval}, author = {M Pesek, A Leonardis, M Marolt} } @misc{2014MProbstFRothlaufJGrahl, title = {Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization}, author = {M Probst, F Rothlauf, J Grahl} } @misc{2014MRFerrier, title = {Toward a Universal Cortical Algorithm: Examining Hierarchical Temporal Memory in Light of Frontal Cortical Function}, author = {MR Ferrier} } @misc{2014MRavanelliBElizaldeKNiGFriedlandFBKessler, title = {Audio Concept Classification With Hierarchical Deep Neural Networks}, author = {M Ravanelli, B Elizalde, K Ni, G Friedland, FB Kessler} } @misc{2014MRavanelliVHDoAJanin, title = {TANDEM-bottleneck feature combination using hierarchical Deep Neural Networks}, author = {M Ravanelli, VH Do, A Janin} } @misc{2014MSahasrabudheAMNamboodiri, title = {Fingerprint Enhancement Using Unsupervised Hierarchical Feature Learning}, author = {M Sahasrabudhe, AM Namboodiri} } @misc{2014MSajjadiMSeyedhosseiniTTasdizen, title = {Disjunctive Normal Networks}, author = {M Sajjadi, M Seyedhosseini, T Tasdizen} } @misc{2014MSchikoraASchikora, title = {Image-Based Analysis to Study Plant Infection with Human Pathogens}, author = {M Schikora, A Schikora} } @misc{2014MSchoelerFWÃ¶rgÃ¶tterJPaponTKulvicius, title = {Unsupervised generation of context-relevant training-sets for visual object recognition employing multilinguality}, author = {M Schoeler, F WÃ¶rgÃ¶tter, J Papon, T Kulvicius} } @misc{2014MSchuldISinayskiyFPetruccione, title = {Simulating a perceptron on a quantum computer}, author = {M Schuld, I Sinayskiy, F Petruccione} } @misc{2014MSlaneyAStolckeDHakkaniTur, title = {The relation of eye gaze and face pose: Potential impact on speech recognition}, author = {M Slaney, A Stolcke, D Hakkani-Tur} } @misc{2014MSongTChambers, title = {Text Mining with the Stanford CoreNLP}, author = {M Song, T Chambers} } @misc{2014MStoehrYAmit, title = {Patch-Based Models of Spectrogram Edges for Phone Classification}, author = {M Stoehr, Y Amit} } @misc{2014MTanakaMOkutomi, title = {A Novel Inference of a Restricted Boltzmann Machine}, author = {M Tanaka, M Okutomi} } @misc{2014MThulinPMasek, title = {Software Quality Evaluation of Face Recognition APIs & Libraries}, author = {M Thulin, P Masek} } @misc{2014MUedaYNishitaniYKanekoAOmote, title = {Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics}, author = {M Ueda, Y Nishitani, Y Kaneko, A Omote} } @misc{2014MUngerLRokachABarEGudesBShapira, title = {Contexto: lessons learned from mobile context inference}, author = {M Unger, L Rokach, A Bar, E Gudes, B Shapira} } @misc{2014MWangTXiaoJLiJZhangCHongZZhang, title = {Minerva: A Scalable and Highly Efficient Training Platform for Deep Learning}, author = {M Wang, T Xiao, J Li, J Zhang, C Hong, Z Zhang} } @misc{2014MWangYChenXWang, title = {Recognition of Handwritten Characters in Chinese Legal Amounts by Stacked Autoencoders}, author = {M Wang, Y Chen, X Wang} } @misc{2014MXiaJGDolfingRSDixonKMGroetheKMisra, title = {Managing Real-time Handwriting Recognition}, author = {M Xia, JG Dolfing, RS Dixon, KM Groethe, K Misra} } @misc{2014MZengLTNguyenBYuOJMengshoelJZhuPWu, title = {Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors}, author = {M Zeng, LT Nguyen, B Yu, OJ Mengshoel, J Zhu, P Wu} } @misc{2014MZhaoCZhuangYWangTSLee, title = {Predictive Encoding of Contextual Relationships for Perceptual Inference, Interpolation and Prediction}, author = {M Zhao, C Zhuang, Y Wang, TS Lee} } @misc{2014NCohenAShashua, title = {SimNets: A Generalization of Convolutional Networks}, author = {N Cohen, A Shashua} } @misc{2014NDLanePGeorgiev, title = {Can Deep Learning Revolutionize Mobile Sensing?}, author = {ND Lane, P Georgiev} } @misc{2014NDhungelGCarneiroAPBradley, title = {Deep Structured learning for mass segmentation from Mammograms}, author = {N Dhungel, G Carneiro, AP Bradley} } @misc{2014NGALAYOUSS, title = {A critical examination of deep learning approaches to automated speech recognition}, author = {NGA LAYOUSS} } @misc{2014NItenDPetko, title = {Learning with serious games: is fun playing the game a predictor of learning success?}, author = {N Iten, D Petko} } @misc{2014NKrÃ¼gerMZillichPJanssenAGBuch, title = {What We Can Learn From the Primate's Visual System}, author = {N KrÃ¼ger, M Zillich, P Janssen, AG Buch} } @misc{2014NMarkuÅ¡MFrljakISPandzicJAhlberg, title = {Fast Localization of Facial Landmark Points}, author = {N MarkuÅ¡, M Frljak, IS Pandzic, J Ahlberg} } @misc{2014NMohajerinSLWaslander, title = {Modular deep Recurrent Neural Network: Application to quadrotors}, author = {N Mohajerin, SL Waslander} } @misc{2014NMondalPPGhosh, title = {On The Dynamical Nature Of Computation}, author = {N Mondal, PP Ghosh} } @misc{2014NNeverovaCWolfGWTaylorFNebout, title = {ModDrop: adaptive multi-modal gesture recognition}, author = {N Neverova, C Wolf, GW Taylor, F Nebout} } @misc{2014NQPhamHSLeDDNguyenTGNgo, title = {A Study of Feature Combination in Gesture Recognition with Kinect}, author = {NQ Pham, HS Le, DD Nguyen, TG Ngo} } @misc{2014NSteenbergen, title = {Chord Recognition with Stacked Denoising Autoencoders}, author = {N Steenbergen} } @misc{2014NTakamuneHKameoka, title = {Maximum Reconstruction Probability Training Of Restricted Boltzmann Machines With Auxiliary Function Approach}, author = {N Takamune, H Kameoka} } @misc{2014NTripathiAJadeja, title = {A Survey of Regularization Methods for Deep Neural Network}, author = {N Tripathi, A Jadeja} } @misc{2014NWahlstrÃ¶mTBSchÃ¶nMPDeisenroth, title = {Learning deep dynamical models from image pixels}, author = {N WahlstrÃ¶m, TB SchÃ¶n, MP Deisenroth} } @misc{2014NWangXGaoDTaoXLi, title = {Facial Feature Point Detection: A Comprehensive Survey}, author = {N Wang, X Gao, D Tao, X Li} } @misc{2014NWiebeAKapoorKMSvore, title = {Quantum Deep Learning}, author = {N Wiebe, A Kapoor, KM Svore} } @misc{2014NdeFreitas, title = {Modelling â€šVisualising and Summarising Documents with a Single Convolutional Neural Network}, author = {N de Freitas} } @misc{2014OBesbesABenazzaBenyahia, title = {Joint Road Network Extraction From A Set Of High Resolution Satellite Images}, author = {O Besbes, A Benazza-Benyahia} } @misc{2014OFiratEAksanIOztekinFTYVural, title = {Learning Deep Temporal Representations for Brain Decoding}, author = {O Firat, E Aksan, I Oztekin, FTY Vural} } @misc{2014OGencogluTVirtanenHHuttunen, title = {Recognition Of Acoustic Events Using Deep Neural Networks}, author = {O Gencoglu, T Virtanen, H Huttunen} } @misc{2014OIrsoyCCardie, title = {Deep Recursive Neural Networks for Compositionality in Language}, author = {O Irsoy, C Cardie} } @misc{2014OIsayevDFourchesENMuratovCOsesKRasch, title = {Large Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints}, author = {O Isayev, D Fourches, EN Muratov, C Oses, K Rasch} } @misc{2014OVinyalsAToshevSBengioDErhan, title = {Show and Tell: A Neural Image Caption Generator}, author = {O Vinyals, A Toshev, S Bengio, D Erhan} } @misc{2014OÄ°rsoyEAlpaydÄ±n, title = {Autoencoder Trees}, author = {O Ä°rsoy, E AlpaydÄ±n} } @misc{2014PAgrawal, title = {Analysis of Multilayer Neural Networks for Object Recognition}, author = {P Agrawal} } @misc{2014PBaldiPSadowskiDWhiteson, title = {Enhanced Higgs to $\ tau^+\ tau^-$ Searches with Deep Learning}, author = {P Baldi, P Sadowski, D Whiteson} } @misc{2014PBezakPBozekYNikitin, title = {Advanced Robotic Grasping System Using Deep Learning}, author = {P Bezak, P Bozek, Y Nikitin} } @misc{2014PBezÃ¡kYRNikitinPBoÅ¾ek, title = {Robotic Grasping System Using Convolutional Neural Networks}, author = {P BezÃ¡k, YR Nikitin, P BoÅ¾ek} } @misc{2014PBodnÃ¡rTGrÃ³szLTÃ³thLGNyÃºl, title = {Localization of Visual Codes in the Dct Domain Using Deep Rectifier Neural Networks}, author = {P BodnÃ¡r, T GrÃ³sz, L TÃ³th, LG NyÃºl} } @misc{2014PDARSMZdenek, title = {Comparative Study Of Machine Learning Techniques For Supervised Classification Of Biomedical Data}, author = {PD AR, SM Zdenek} } @misc{2014PFengMYuSMNaqviJAChambers, title = {Deep learning for posture analysis in fall detection}, author = {P Feng, M Yu, SM Naqvi, JA Chambers} } @misc{2014PFoggiaASaggeseNStrisciuglioMVento, title = {Exploiting the deep learning paradigm for recognizing human actions}, author = {P Foggia, A Saggese, N Strisciuglio, M Vento} } @misc{2014PHOPinheiroRCollobert, title = {Weakly Supervised Object Segmentation with 004 dwaeConvolutional Neural Networks}, author = {PHO Pinheiro, R Collobert} } @misc{2014PHoneine, title = {Analyzing sparse dictionaries for online learning with kernels}, author = {P Honeine} } @misc{2014PHuangYHuangWWangLWang, title = {Deep Embedding Network for Clustering}, author = {P Huang, Y Huang, W Wang, L Wang} } @misc{2014PHÃ¡la, title = {Spectral classification using convolutional neural networks}, author = {P HÃ¡la} } @misc{2014PKMuthukumarAWBlack, title = {A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis}, author = {PK Muthukumar, AW Black} } @misc{2014PMehtaDJSchwab, title = {An exact mapping between the Variational Renormalization Group and Deep Learning}, author = {P Mehta, DJ Schwab} } @misc{2014PPRoyYChherawalaMCheriet, title = {Deep-Belief-Network based Rescoring for Handwritten Word Recognition}, author = {PP Roy, Y Chherawala, M Cheriet} } @misc{2014PPrzymus, title = {Query Optimization in Heterogeneous Cpu/gpu Environment for Time Series Databases}, author = {P Przymus} } @misc{2014PRAFirminoPSGdeMattosNetoTAEFerreira, title = {Error Modeling Approach to Improve Time Series Forecasters}, author = {PRA Firmino, PSG de Mattos Neto, TAE Ferreira} } @misc{2014PSprechmannAMBronsteinGSapiro, title = {Supervised non-negative matrix factorization for audio source separation}, author = {P Sprechmann, AM Bronstein, G Sapiro} } @misc{2014PXieMBilenkoTFinleyRGiladBachrachKLauter, title = {Crypto-nets: Neural Networks Over En-crypted Data}, author = {P Xie, M Bilenko, T Finley, R Gilad-Bachrach, K Lauter} } @misc{2014PXuMYeXLiQLiuYYangJDing, title = {Dynamic Background Learning through Deep Auto-encoder Networks}, author = {P Xu, M Ye, X Li, Q Liu, Y Yang, J Ding} } @misc{2014PZhangSLiYZhou, title = {An Algorithm of Quantum Restricted Boltzmann Machine Network Based on Quantum Gates and Its Application}, author = {P Zhang, S Li, Y Zhou} } @misc{2014QBNguyenTTVuCMLuong, title = {Improving Acoustic Model for Vietnamese Large Vocabulary Continuous Speech Recognition System Using Deep Bottleneck Features}, author = {QB Nguyen, TT Vu, CM Luong} } @misc{2014QChenMAbediniRGarnaviXLiang, title = {Ibm research australia at lifeclef2014: Plant identification task}, author = {Q Chen, M Abedini, R Garnavi, X Liang} } @misc{2014QHPhanHFuABChan, title = {Look Closely: Learning Exemplar Patches for Recognizing Textiles from Product Images}, author = {QH Phan, H Fu, AB Chan} } @misc{2014QKongXFengYLi, title = {Music Genre Classification Using Convolutional Neural Network}, author = {Q Kong, X Feng, Y Li} } @misc{2014QQiuGSapiroABronstein, title = {Random Forests Can Hash}, author = {Q Qiu, G Sapiro, A Bronstein} } @misc{2014QWangYWangZWang, title = {Online Smart Face Morphing Engine with Prior Constraints and Local Geometry Preservation}, author = {Q Wang, Y Wang, Z Wang} } @misc{2014RCYuanHYanXMZhouFCDiLXLi, title = {Application and Architecture of Power Dispatching & Distribution System Using Big Data Technology}, author = {RC Yuan, H Yan, XM Zhou, FC Di, LX Li} } @misc{2014RChalasaniJCPrincipe, title = {Context Dependent Encoding using Convolutional Dynamic Networks}, author = {R Chalasani, JC Principe} } @misc{2014RChellappa, title = {Visual Domain Adaptation: A Survey of Recent Advances}, author = {R Chellappa} } @misc{2014RDingBZhaoSChen, title = {A neuromorphic categorization system with Online Sequential Extreme Learning}, author = {R Ding, B Zhao, S Chen} } @misc{2014RFernandezARendel, title = {Hybrid Predictive Model For Enhancing Prosodic Expressiveness}, author = {R Fernandez, A Rendel} } @misc{2014RFrassettoNogueiraRdeAlencarLotufo, title = {Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns}, author = {R Frassetto Nogueira, R de Alencar Lotufo} } @misc{2014RGhoshAMishraGOrchardNVThakor, title = {Real-time object recognition and orientation estimation using an event-based camera and Cnn}, author = {R Ghosh, A Mishra, G Orchard, NV Thakor} } @misc{2014RGirshickFIandolaTDarrellJMalik, title = {Deformable Part Models are Convolutional Neural Networks}, author = {R Girshick, F Iandola, T Darrell, J Malik} } @misc{2014RGiryesGSapiroAMBronstein, title = {On the Stability of Deep Networks}, author = {R Giryes, G Sapiro, AM Bronstein} } @misc{2014RGlattJCFreireJrDJBSSampaio, title = {Proposal for a Deep Learning Architecture for Activity Recognition}, author = {R Glatt, JC Freire Jr, DJBS Sampaio} } @misc{2014RGoroshinJBrunaJTompsonDEigenYLeCun, title = {Unsupervised Learning of Spatiotemporally Coherent Metrics}, author = {R Goroshin, J Bruna, J Tompson, D Eigen, Y LeCun} } @misc{2014RHeMZhangLWangYJiQYin, title = {Cross-Modal Learning via Pairwise Constraints}, author = {R He, M Zhang, L Wang, Y Ji, Q Yin} } @misc{2014RJKannanSSubramanian, title = {An Adaptive Approach of Tamil Character Recognition Using Deep Learning with Big Data-A Survey}, author = {RJ Kannan, S Subramanian} } @misc{2014RJohnsonTZhang, title = {Effective Use of Word Order for Text Categorization with Convolutional Neural Networks}, author = {R Johnson, T Zhang} } @misc{2014RKSrivastavaJMasciFGomezJSchmidhuber, title = {Understanding Locally Competitive Networks}, author = {RK Srivastava, J Masci, F Gomez, J Schmidhuber} } @misc{2014RKirosRSalakhutdinovRSZemel, title = {Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models}, author = {R Kiros, R Salakhutdinov, RS Zemel} } @misc{2014RKumarAKCheema, title = {Gpu Implementation of a Deep Learning Network for Financial Prediction}, author = {R Kumar, AK Cheema} } @misc{2014RKumarRKSharmaASharma, title = {Recognition of Multi-Stroke Based Online Handwritten Gurmukhi Aksharas}, author = {R Kumar, RK Sharma, A Sharma} } @misc{2014RLiFFengXWangPLuBLi, title = {Obtaining Cross-modal Similarity Metric with Deep Neural Architecture}, author = {R Li, F Feng, X Wang, P Lu, B Li} } @misc{2014RLivniSShalevShwartzOShamir, title = {On the Computational Efficiency of Training Neural Networks}, author = {R Livni, S Shalev-Shwartz, O Shamir} } @misc{2014RMCCOPPIN, title = {An Evolutionary Approximation to Contrastive Divergence in Convolutional Restricted Boltzmann Machines}, author = {R MCCOPPIN} } @misc{2014RMGolden, title = {Stochastic Descent Analysis of Representation Learning Algorithms}, author = {RM Golden} } @misc{2014RMKeller, title = {Machine Learning Applied to Musical Improvisation}, author = {RM Keller} } @misc{2014RMMenchÃ³nLaraJLSanchoGÃ³mez, title = {Fully automatic segmentation of ultrasound common carotid artery images based on machine learning}, author = {RM MenchÃ³n-Lara, JL Sancho-GÃ³mez} } @misc{2014RMinBBai, title = {High-Order Semi-RBMs and Deep Gated Neural Networks for Feature Interaction Identification and Non-Linear Semantic Indexing}, author = {R Min, B Bai} } @misc{2014RMohan, title = {Deep Deconvolutional Networks for Scene Parsing}, author = {R Mohan} } @misc{2014RRVariorGWangJLu, title = {Learning Invariant Color Features for Person Re-Identification}, author = {RR Varior, G Wang, J Lu} } @misc{2014RRanganathLTangLCharlinDMBlei, title = {Deep Exponential Families}, author = {R Ranganath, L Tang, L Charlin, DM Blei} } @misc{2014RSAdepu, title = {Temporal Coherence in Energy-based Deep Learning Machines for Action Recognition}, author = {RS Adepu} } @misc{2014RSDixonJGDolfingUMeierJRBellegarda, title = {Integrating Stroke-distribution Information Into Spatial Feature Extraction For Automatic Handwriting Recognition}, author = {RS Dixon, JG Dolfing, U Meier, JR Bellegarda} } @misc{2014RSerizelDGiuliani, title = {Vocal Tract Length Normalisation Approaches To Dnn-based Children's And Adults'speech Recognition}, author = {R Serizel, D Giuliani} } @misc{2014RSerizelDGiulianiFBKFBK, title = {Deep neural network adaptation for children's and adults' speech recognition}, author = {R Serizel, D Giuliani, FBK FBK} } @misc{2014RVedantamCLZitnickDParikh, title = {CIDEr: Consensus-based Image Description Evaluation}, author = {R Vedantam, CL Zitnick, D Parikh} } @misc{2014RWangCHanYWuTGuo, title = {Fingerprint Classification Based on Depth Neural Network}, author = {R Wang, C Han, Y Wu, T Guo} } @misc{2014RYangSGeKXieSChen, title = {Eye Localization Based on Multi-Channel Correlation Filter Bank}, author = {R Yang, S Ge, K Xie, S Chen} } @misc{2014RZengJWuZShaoLSenhadjiHShu, title = {Quaternion softmax classifier}, author = {R Zeng, J Wu, Z Shao, L Senhadji, H Shu} } @misc{2014SABahrainianMLiwickiADengel, title = {Fuzzy Subjective Sentiment Phrases: A Context Sensitive and Self-Maintaining Sentiment Lexicon}, author = {SA Bahrainian, M Liwicki, A Dengel} } @misc{2014SAfsharLGeorgeJTapsonAvanSchaik, title = {Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels}, author = {S Afshar, L George, J Tapson, A van Schaik} } @misc{2014SAvilaDMoreiraMPerezDMoraesICota, title = {Recod at MediaEval 2014: Violent Scenes Detection Task}, author = {S Avila, D Moreira, M Perez, D Moraes, I Cota} } @misc{2014SBuPHanZLiuJHan, title = {Local deep feature learning framework for 3d shape}, author = {S Bu, P Han, Z Liu, J Han} } @misc{2014SChatzis, title = {A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis}, author = {S Chatzis} } @misc{2014SChenYWang, title = {Convolutional Neural Network and Convex Optimization}, author = {S Chen, Y Wang} } @misc{2014SChetlurCWoolleyPVandermerschJCohen, title = {cuDNN: Efficient Primitives for Deep Learning}, author = {S Chetlur, C Woolley, P Vandermersch, J Cohen} } @misc{2014SDSarmaMFreedmanCNayak, title = {Majorana Zero Modes and Topological Quantum Computation}, author = {SD Sarma, M Freedman, C Nayak} } @misc{2014SDingNZhangXXuLGuoJZhang, title = {Deep Extreme Learning Machine and Its Application in Eeg Classification}, author = {S Ding, N Zhang, X Xu, L Guo, J Zhang} } @misc{2014SEKahouPFroumentyCPal, title = {Facial Expression Analysis Based on High Dimensional Binary Features}, author = {SE Kahou, P Froumenty, C Pal} } @misc{2014SElfwingEUchibeKDoya, title = {Expected energy-based restricted Boltzmann machine for classification}, author = {S Elfwing, E Uchibe, K Doya} } @misc{2014SFerrerTRuiz, title = {Travel Behavior Characterization Using Raw Accelerometer Data Collected from Smartphones}, author = {S Ferrer, T Ruiz} } @misc{2014SFeyzabadi, title = {Joint Deep Learning for Car Detection}, author = {S Feyzabadi} } @misc{2014SGaoLDuanITsang, title = {DEFEATnet--A Deep Conventional Image Representation for Image Classification}, author = {S Gao, L Duan, I Tsang} } @misc{2014SGinosarDHaasTBrownJMalik, title = {Detecting People in Cubist Art}, author = {S Ginosar, D Haas, T Brown, J Malik} } @misc{2014SGoyalPBenjamin, title = {Object Recognition Using Deep Neural Networks: A Survey}, author = {S Goyal, P Benjamin} } @misc{2014SGuLRigazio, title = {Towards Deep Neural Network Architectures Robust to Adversarial Examples}, author = {S Gu, L Rigazio} } @misc{2014SHussainSCLiuABasu, title = {Hardware-Amenable Structural Learning for Spike-based Pattern Classification using a Simple Model of Active Dendrites}, author = {S Hussain, SC Liu, A Basu} } @misc{2014SKhorramHSametiSKing, title = {Soft context clustering for F0 modeling in HMM-based speech synthesis}, author = {S Khorram, H Sameti, S King} } @misc{2014SKimZYuRMKilMLee, title = {Deep learning of support vector machines with class probability output networks}, author = {S Kim, Z Yu, RM Kil, M Lee} } @misc{2014SMKhalighRazaviNKriegeskorte, title = {Deep supervised, but not unsupervised, models may explain It cortical representation}, author = {SM Khaligh-Razavi, N Kriegeskorte} } @misc{2014SMoonSKimHWang, title = {Multimodal Transfer Deep Learning for Audio Visual Recognition}, author = {S Moon, S Kim, H Wang} } @misc{2014SNieZWangQJi, title = {A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling}, author = {S Nie, Z Wang, Q Ji} } @misc{2014SOgnawalaJBayer, title = {Regularizing Recurrent Networks-On Injected Noise and Norm-based Methods}, author = {S Ognawala, J Bayer} } @misc{2014SOzairYBengio, title = {Deep Directed Generative Autoencoders}, author = {S Ozair, Y Bengio} } @misc{2014SPaisitkriangkraiCShenAHengel, title = {Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning}, author = {S Paisitkriangkrai, C Shen, A Hengel} } @misc{2014SQiFWangXWangYGuanJWeiJGuan, title = {Multiple level visual semantic fusion method for image re-ranking}, author = {S Qi, F Wang, X Wang, Y Guan, J Wei, J Guan} } @misc{2014SReedHLeeDAnguelovCSzegedyDErhan, title = {Training Deep Neural Networks on Noisy Labels with Bootstrapping}, author = {S Reed, H Lee, D Anguelov, C Szegedy, D Erhan} } @misc{2014SSTirumala, title = {Implementation of Evolutionary Algorithms for Deep Architectures}, author = {SS Tirumala} } @misc{2014SSalehiASelamatRMasinchiHFujita, title = {The Synergistic Combination of Particle Swarm Optimization and Fuzzy Sets to Design Granular Classifier}, author = {S Salehi, A Selamat, R Masinchi, H Fujita} } @misc{2014SSarkarVVenugopalanKReddyMGieringJRyde, title = {Occlusion Edge Detection in Rgb-d Frames using Deep Convolutional Networks}, author = {S Sarkar, V Venugopalan, K Reddy, M Giering, J Ryde} } @misc{2014SShalevShwartz, title = {SelfieBoost: A Boosting Algorithm for Deep Learning}, author = {S Shalev-Shwartz} } @misc{2014SShekharVMPatelHVNguyenRChellappa, title = {Coupled Projections for Semi-supervised Adaptation of Dictionaries}, author = {S Shekhar, VM Patel, HV Nguyen, R Chellappa} } @misc{2014SSickertERodnerJDenzler, title = {Semantic Volume Segmentation with Iterative Context Integration}, author = {S Sickert, E Rodner, J Denzler} } @misc{2014SSoatto, title = {Visual Scene Representations: Sufficiency, Minimality, Invariance and Approximations}, author = {S Soatto} } @misc{2014SSoattoJDongNKarianakis, title = {Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures}, author = {S Soatto, J Dong, N Karianakis} } @misc{2014SThomasCChatelainLHeutteTPaquet, title = {A deep Hmm model for multiple keywords spotting in handwritten documents}, author = {S Thomas, C Chatelain, L Heutte, T Paquet} } @misc{2014STuYXueJWangXHuangXZhang, title = {Learning Block Group Sparse Representation Combined with Convolutional Neural Networks for Rgb-d Object Recognition}, author = {S Tu, Y Xue, J Wang, X Huang, X Zhang} } @misc{2014SVenugopalanHXuJDonahueMRohrbach, title = {Translating Videos to Natural Language Using Deep Recurrent Neural Networks}, author = {S Venugopalan, H Xu, J Donahue, M Rohrbach} } @misc{2014SWoÅºniakADAlmÃ¡siVCristeaYLeblebici, title = {Review of Advances in Neural Networks: Neural Design Technology Stack}, author = {S WoÅºniak, AD AlmÃ¡si, V Cristea, Y Leblebici} } @misc{2014SXuXMeiWDongXSunXShenXZhang, title = {Depth of field rendering via adaptive recursive filtering}, author = {S Xu, X Mei, W Dong, X Sun, X Shen, X Zhang} } @misc{2014SXueHJiangLDai, title = {Speaker adaptation of hybrid Nn/hmm model for speech recognition based on singular value decomposition}, author = {S Xue, H Jiang, L Dai} } @misc{2014SXueOAbdelHamidHJiangLDaiQLiu, title = {Fast adaptation of deep neural network based on discriminant codes for speech recognition}, author = {S Xue, O Abdel-Hamid, H Jiang, L Dai, Q Liu} } @misc{2014SYangPLuoCCLoyKWShumXTang, title = {Deep Representation Learning with Target Coding}, author = {S Yang, P Luo, CC Loy, KW Shum, X Tang} } @misc{2014SYangPLuoCCLoyKWShumXTangDeepRepresentationLearning, title = {Deep Representation Learning with Target Coding Supplementary Material}, author = {S Yang, P Luo, CC Loy, KW Shum, X Tang} } @misc{2014SZLiBYuWWuSZSuRRJi, title = {Feature learning based on Sae-pca network for Human gesture recognition in Rgbd images}, author = {SZ Li, B Yu, W Wu, SZ Su, RR Ji} } @misc{2014SZhangAChoromanskaYLeCun, title = {Deep learning with Elastic Averaging Sgd}, author = {S Zhang, A Choromanska, Y LeCun} } @misc{2014SZhangFQiaoMLiu, title = {Performance Prediction by Deep Learning Methods for Semiconductor Manufacturing}, author = {S Zhang, F Qiao, M Liu} } @misc{2014SZhangKKang, title = {Learning High-level Features by Deep Boltzmann Machines for Handwriting Digits Recogintion}, author = {S Zhang, K Kang} } @misc{2014SZhaoHYaoSZhaoXJiangXJiang, title = {Multi-modal microblog classification via multi-task learning}, author = {S Zhao, H Yao, S Zhao, X Jiang, X Jiang} } @misc{2014SZhouQChenXWang, title = {Deep Adaptive Networks for Visual Data Classification}, author = {S Zhou, Q Chen, X Wang} } @misc{2014TAOYANGXZHAOBLINTAOZENGSJIJYE, title = {Automated Gene Expression Pattern Annotation In The Mouse Brain}, author = {TAO YANG, X ZHAO, B LIN, TAO ZENG, S JI, J YE} } @misc{2014TAdams, title = {Brain Edge Detection}, author = {T Adams} } @misc{2014TBroschRTam, title = {Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2d and 3d Images}, author = {T Brosch, R Tam} } @misc{2014TChenDBorthTDarrellSFChang, title = {DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks}, author = {T Chen, D Borth, T Darrell, SF Chang} } @misc{2014TChilimbiYSuzueJApacibleKKalyanaraman, title = {Project Adam: Building an Efficient and Scalable Deep Learning Training System}, author = {T Chilimbi, Y Suzue, J Apacible, K Kalyanaraman} } @misc{2014TDOrathanadu, title = {A Method For Extracting Information From The Web Using Deep Learning Algorithm}, author = {TD Orathanadu} } @misc{2014TGrÃ³szPBodnÃ¡rLTÃ³thLGNyÃºl, title = {Qr Code Localization Using Deep Neural Networks}, author = {T GrÃ³sz, P BodnÃ¡r, L TÃ³th, LG NyÃºl} } @misc{2014THassnerSHarelEPazREnbar, title = {Effective Face Frontalization in Unconstrained Images}, author = {T Hassner, S Harel, E Paz, R Enbar} } @misc{2014THoritaITakanamiMAkibaMTerauchiTKanno, title = {A GPGPU-Based Acceleration of Fault-Tolerant Mlp Learnings}, author = {T Horita, I Takanami, M Akiba, M Terauchi, T Kanno} } @misc{2014TKoriyamaTNoseTKobayashi, title = {Parametric Speech Synthesis Using Local and Global Sparse Gaussian}, author = {T Koriyama, T Nose, T Kobayashi} } @misc{2014TLMcDonell, title = {Optimising Purely Functional Gpu Programs (Thesis)}, author = {TL McDonell} } @misc{2014TLPainePKhorramiWHanTSHuang, title = {An Analysis of Unsupervised Pre-training in Light of Recent Advances}, author = {TL Paine, P Khorrami, W Han, TS Huang} } @misc{2014TLiuMLi, title = {Improving relation descriptor extraction with word embeddings and cluster features}, author = {T Liu, M Li} } @misc{2014TManiakCJayneRIqbalFDoctor, title = {Automated intelligent system for sound signalling device quality assurance}, author = {T Maniak, C Jayne, R Iqbal, F Doctor} } @misc{2014TNSainathBKingsburyGSaonHSoltau, title = {Deep convolutional neural networks for large-scale speech tasks}, author = {TN Sainath, B Kingsbury, G Saon, H Soltau} } @misc{2014TNakashikaTTakiguchiYAriki, title = {Voice Conversion Using Rnn Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines}, author = {T Nakashika, T Takiguchi, Y Ariki} } @misc{2014TNakashikaTYoshiokaTTakiguchiYAriki, title = {Dysarthric Speech Recognition Using a Convolutive Bottleneck Network}, author = {T Nakashika, T Yoshioka, T Takiguchi, Y Ariki} } @misc{2014TPLillicrapDCowndenDBTweedCJAkerman, title = {Random feedback weights support learning in deep neural networks}, author = {TP Lillicrap, D Cownden, DB Tweed, CJ Akerman} } @misc{2014TSLiCMHu, title = {The Application of Sift Image Matching in the Information Query Based on Mpi Acceleration}, author = {TS Li, CM Hu} } @misc{2014TUnterthinerAMayrGKlambauerMSteijaert, title = {Multi-Task Deep Networks for Drug Target Prediction}, author = {T Unterthiner, A Mayr, G Klambauer, M Steijaert} } @misc{2014TVNguyenCLuJSepulvedaSYan, title = {Adaptive Nonparametric Image Parsing}, author = {TV Nguyen, C Lu, J Sepulveda, S Yan} } @misc{2014TXiaoJZhangKYangYPengZZhang, title = {Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification}, author = {T Xiao, J Zhang, K Yang, Y Peng, Z Zhang} } @misc{2014TXiaoYXuKYangJZhangYPengZZhang, title = {The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification}, author = {T Xiao, Y Xu, K Yang, J Zhang, Y Peng, Z Zhang} } @misc{2014TYDuJunXYongLCHDaiLirong, title = {Speech Separation of A Target Speaker Based on Deep Neural Networks}, author = {TY Du Jun, X Yong, LCH Dai Lirong} } @misc{2014TYamashitaMTanakaEYoshidaYYamauchi, title = {To be Bernoulli or to be Gaussian, for a Restricted Boltzmann Machine}, author = {T Yamashita, M Tanaka, E Yoshida, Y Yamauchi} } @misc{2014TYanhuiDJunXYongDLirongLChinHui, title = {Deep Neural Network Based Speech Separation for Robust Speech Recognition}, author = {T Yanhui, D Jun, X Yong, D Lirong, L Chin-Hui} } @misc{2014TYoshiokaMJFGales, title = {Environmentally robust Asr front-end for deep neural network acoustic models}, author = {T Yoshioka, MJF Gales} } @misc{2014TZhaoYZhaoXChen, title = {Building an ensemble of Cd-dnn-hmm acoustic model using random forests of phonetic decision trees}, author = {T Zhao, Y Zhao, X Chen} } @misc{2014USÃ¼mbÃ¼lAZlateskiAVishwanathanRHMasland, title = {Automated computation of arbor densities: a step toward identifying neuronal cell types}, author = {U SÃ¼mbÃ¼l, A Zlateski, A Vishwanathan, RH Masland} } @misc{2014VDLuongLWangGXiao, title = {Action Recognition Using Hierarchical Independent Subspace Analysis with Trajectory}, author = {VD Luong, L Wang, G Xiao} } @misc{2014VJRRipollAWojdelPRamosERomeroJBrugada, title = {Assessment of Electrocardiograms with Pretraining and Shallow Networks}, author = {VJR Ripoll, A Wojdel, P Ramos, E Romero, J Brugada} } @misc{2014VJavierTraverPLatorreCarmona, title = {Human gesture recognition using three-dimensional integral imaging}, author = {V Javier Traver, P Latorre-Carmona} } @misc{2014VKumarGCNandiRKala, title = {Static hand gesture recognition using stacked Denoising Sparse Autoencoders}, author = {V Kumar, GC Nandi, R Kala} } @misc{2014VTurchenkoVGolovko, title = {Parallel batch pattern training algorithm for deep neural network}, author = {V Turchenko, V Golovko} } @misc{2014WAdamsKPlis, title = {Energy Based Models and Boltzmann Machines (Cont.)}, author = {W Adams, K Plis} } @misc{2014WChanILaneSGradientsMMomentumGDecay, title = {Distributed Asynchronous Optimization of Convolutional Neural Networks}, author = {W Chan, I Lane, S Gradients, M Momentum, G Decay} } @misc{2014WChenGGuo, title = {TriViews: A general framework to use 3d depth data effectively for action recognition}, author = {W Chen, G Guo} } @misc{2014WDingRWangFMaoGTaylor, title = {Theano-based Large-Scale Visual Recognition with Multiple GPUs}, author = {W Ding, R Wang, F Mao, G Taylor} } @misc{2014WHLeleCaoFSun, title = {A Deep and Stable Extreme Learning Approach for Classification and Regressionâ‹†}, author = {WH Le-le Cao, F Sun} } @misc{2014WHe, title = {Deep neural network based load forecast}, author = {W He} } @misc{2014WHouXGao, title = {Saliency-guided deep framework for image quality assessment}, author = {W Hou, X Gao} } @misc{2014WHuYQianFKSoongYWang, title = {Improved Mispronunciation Detection with Deep Neural Network Trained Acoustic Models and Transfer Learning based Logistic Regression Classifiers}, author = {W Hu, Y Qian, FK Soong, Y Wang} } @misc{2014WHuangFSun, title = {A Deep and Stable Extreme Learning Approach for Classification and Regression}, author = {W Huang, F Sun} } @misc{2014WLRZhaoTXiaoXWang, title = {DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification}, author = {WLR Zhao, T Xiao, X Wang} } @misc{2014WLiLWangYZhouJDinesMMagimaiDoss, title = {Feature Mapping of Multiple Beamformed Sources for Robust Overlapping Speech Recognition Using a Microphone Array}, author = {W Li, L Wang, Y Zhou, J Dines, M Magimai-Doss} } @misc{2014WOuyangPLuoXZengSQiuYTianHLiSYang, title = {DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection}, author = {W Ouyang, P Luo, X Zeng, S Qiu, Y Tian, H Li, S Yang} } @misc{2014WOuyangXWangXZengSQiuPLuoYTianHLi, title = {DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection}, author = {W Ouyang, X Wang, X Zeng, S Qiu, P Luo, Y Tian, H Li} } @misc{2014WRenYYuJZhangKHuang, title = {Learning Convolutional NonLinear Features for K Nearest Neighbor Image Classification}, author = {W Ren, Y Yu, J Zhang, K Huang} } @misc{2014WSongWXuLLiuHWang, title = {Cnu System in Ntcir-11 IMine Task}, author = {W Song, W Xu, L Liu, H Wang} } @misc{2014WWLiuMCaiHYuanXBShiWQZhangJLiu, title = {Phonotactic language recognition based on Dnn-hmm acoustic model}, author = {WW Liu, M Cai, H Yuan, XB Shi, WQ Zhang, J Liu} } @misc{2014WYuFZhuangQHeZShi, title = {Learning Deep Representations via Extreme Learning Machines}, author = {W Yu, F Zhuang, Q He, Z Shi} } @misc{2014WZarembaISutskever, title = {Learning to Execute}, author = {W Zaremba, I Sutskever} } @misc{2014WZhangRLiHDengLWangWLinSJiDShen, title = {Deep Convolutional Neural Networks for Multi-Modality Isointense Infant Brain Image Segmentation}, author = {W Zhang, R Li, H Deng, L Wang, W Lin, S Ji, D Shen} } @misc{2014XCYinCYangWYPeiHWHao, title = {Shallow Classification or Deep Learning: An Experimental Study}, author = {XC Yin, C Yang, WY Pei, HW Hao} } @misc{2014XChangFNieZMaYYangXZhou, title = {A Convex Formulation for Spectral Shrunk Clustering}, author = {X Chang, F Nie, Z Ma, Y Yang, X Zhou} } @misc{2014XChenAYuille, title = {Parsing Occluded People by Flexible Compositions}, author = {X Chen, A Yuille} } @misc{2014XChenXChengSMallat, title = {Unsupervised Deep Haar Scattering on Graphs}, author = {X Chen, X Cheng, S Mallat} } @misc{2014XFrazaoLAAlexandre, title = {Weighted Convolutional Neural Network Ensemble}, author = {X Frazao, LA Alexandre} } @misc{2014XGuoSSinghHLeeRLewisXWang, title = {Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning}, author = {X Guo, S Singh, H Lee, R Lewis, X Wang} } @misc{2014XJHeZDYiJLiuYZWang, title = {Defect Detecting Technology Based on Machine Vision of Industrial Parts}, author = {XJ He, ZD Yi, J Liu, YZ Wang} } @misc{2014XJWu, title = {Random Cascaded-Regression Copse for Robust Facial Landmark Detection}, author = {XJ Wu} } @misc{2014XLZhang, title = {Deep Distributed Random Samplings for Supervised Learning: An Alternative to Random Forests?}, author = {XL Zhang} } @misc{2014XLiXWu, title = {Labeling unsegmented sequence data with Dnn-hmm and its application for speech recognition}, author = {X Li, X Wu} } @misc{2014XLiXWuDecisiontreebased, title = {Decision tree based state tying for speech recognition using Dnn derived embeddings}, author = {X Li, X Wu} } @misc{2014XLiuKDuhYMatsumotoTIwakura, title = {Learning Character Representations for Chinese Word Segmentation}, author = {X Liu, K Duh, Y Matsumoto, T Iwakura} } @misc{2014XLuZLinHJinJYangJZWang, title = {Rapid: Rating Pictorial Aesthetics using Deep Learning}, author = {X Lu, Z Lin, H Jin, J Yang, JZ Wang} } @misc{2014XLvSWangXLiSJiang, title = {Combining heterogenous features for 3d hand-held object recognition}, author = {X Lv, S Wang, X Li, S Jiang} } @misc{2014XNFanSZhang, title = {lncRNA-MFDL: Identification of human long non-coding RNAs by fusing multiple features and using deep learning}, author = {XN Fan, S Zhang} } @misc{2014XOuLYanHLingCLiuMLiu, title = {Inductive Transfer Deep Hashing for Image Retrieval}, author = {X Ou, L Yan, H Ling, C Liu, M Liu} } @misc{2014XPengRYanBZhaoHTangZYi, title = {Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification}, author = {X Peng, R Yan, B Zhao, H Tang, Z Yi} } @misc{2014XQinSXiao, title = {Transparent-supported radiance regression function}, author = {X Qin, S Xiao} } @misc{2014XTangXWan, title = {Learning Bilingual Embedding Model for Cross-Language Sentiment Classification}, author = {X Tang, X Wan} } @misc{2014XTianGYuPLi, title = {Spammer detection on Sina Micro-Blog}, author = {X Tian, G Yu, P Li} } @misc{2014XWangDFFouheyAGupta, title = {Designing Deep Networks for Surface Normal Estimation}, author = {X Wang, DF Fouhey, A Gupta} } @misc{2014XWangJChenWFangCLiangCZhangRHu, title = {Pedestrian Detection From Salient Regions}, author = {X Wang, J Chen, W Fang, C Liang, C Zhang, R Hu} } @misc{2014XWangaWTanbHWuc, title = {An Innovative Svm for Wheat Seed Quality Estimationâ‹†}, author = {X Wanga, W Tanb, H Wuc} } @misc{2014XXuAShimadaRTaniguchi, title = {Mlia at ImageCLFE 2014 Scalable Concept Image Annotation Challenge}, author = {X Xu, A Shimada, R Taniguchi} } @misc{2014XYangJLiu, title = {Deep belief network based Crf for spoken language understanding}, author = {X Yang, J Liu} } @misc{2014XZhangHXiongWZhouQTian, title = {Fused one-vs-all mid-level features for fine-grained visual categorization}, author = {X Zhang, H Xiong, W Zhou, Q Tian} } @misc{2014XZhengJWeiWLuQFangJDang, title = {Mapping between ultrasound and vowel speech using Dnn framework}, author = {X Zheng, J Wei, W Lu, Q Fang, J Dang} } @misc{2014YBYuanGYDavidSZhao, title = {Machine Learning in Intelligent Video and Automated Monitoring}, author = {YB Yuan, GY David, S Zhao} } @misc{2014YBarNLevyLWolf, title = {Classification of Artistic Styles using Binarized Features Derived from a Deep Neural Network}, author = {Y Bar, N Levy, L Wolf} } @misc{2014YBengioIJGoodfellowACourville, title = {Deep Learning}, author = {Y Bengio, IJ Goodfellow, A Courville} } @misc{2014YBurdaRBGrosseRSalakhutdinov, title = {Accurate and Conservative Estimates of Mrf Log-likelihood using Reverse Annealing}, author = {Y Burda, RB Grosse, R Salakhutdinov} } @misc{2014YCSuTHChiuCYYehHHuangWHHsu, title = {Transfer Learning for Video Recognition with Scarce Training Data}, author = {YC Su, TH Chiu, CY Yeh, H Huang, WH Hsu} } @misc{2014YCaoYChenDKhosla, title = {Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition}, author = {Y Cao, Y Chen, D Khosla} } @misc{2014YChenMZhuNEpainCJin, title = {Unsupervised feature learning on monaural Doa estimation using convolutional deep belief networks}, author = {Y Chen, M Zhu, N Epain, C Jin} } @misc{2014YChengXZhaoKHuangTTan, title = {Semi-Supervised Learning for Rgb-d Object Recognition}, author = {Y Cheng, X Zhao, K Huang, T Tan} } @misc{2014YGanTYangCHe, title = {A Deep Graph Embedding Network Model for Face Recognition}, author = {Y Gan, T Yang, C He} } @misc{2014YGanTZhuoCHe, title = {Image Classification with A Deep Network Model based on Compressive Sensing}, author = {Y Gan, T Zhuo, C He} } @misc{2014YGaninVLempitsky, title = {Unsupervised Domain Adaptation by Backpropagation}, author = {Y Ganin, V Lempitsky} } @misc{2014YHuDYiSLiaoZLeiSZLi, title = {Cross Dataset Person Re-identification}, author = {Y Hu, D Yi, S Liao, Z Lei, SZ Li} } @misc{2014YJiangDWangRLiuZFeng, title = {Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks}, author = {Y Jiang, D Wang, R Liu, Z Feng} } @misc{2014YJinHPTan, title = {Unisense: A Unified and Sustainable Sensing and Transport Architecture for Large Scale and Heterogeneous Sensor Networks}, author = {Y Jin, HP Tan} } @misc{2014YLiLMPoXXuLFengFYuanCHCheung, title = {No-reference image quality assessment with shearlet transform and deep neural Networks}, author = {Y Li, LM Po, X Xu, L Feng, F Yuan, CH Cheung} } @misc{2014YLiuFTangZZeng, title = {Feature Selection Based on Dependency Margin}, author = {Y Liu, F Tang, Z Zeng} } @misc{2014YLiuLQinZChengYZhangWZhangQHuang, title = {Da-ccd: A novel action representation by deep architecture of local depth feature}, author = {Y Liu, L Qin, Z Cheng, Y Zhang, W Zhang, Q Huang} } @misc{2014YLiuPLasangMSiegelQSun, title = {Geodesic Invariant Feature (gif): A Local Descriptor in Depth}, author = {Y Liu, P Lasang, M Siegel, Q Sun} } @misc{2014YLvYDuanWKangZLiFYWang, title = {Traffic Flow Prediction With Big Data: A Deep Learning Approach}, author = {Y Lv, Y Duan, W Kang, Z Li, FY Wang} } @misc{2014YMaJDangWLi, title = {Research on deep neural network's hidden layers in phoneme recognition}, author = {Y Ma, J Dang, W Li} } @misc{2014YMaZGuoJSuYChenXDuYYangCLiYLin, title = {Deep learning for fault diagnosis based on multi-sourced heterogeneous data}, author = {Y Ma, Z Guo, J Su, Y Chen, X Du, Y Yang, C Li, Y Lin} } @misc{2014YPuXYuanLCarin, title = {Bayesian Deep Deconvolutional Learning}, author = {Y Pu, X Yuan, L Carin} } @misc{2014YSChouCWSu, title = {Personalized Face Image Retrieval Based On Gmkl}, author = {YS Chou, CW Su} } @misc{2014YSJeongRJayaramam, title = {Support Vector-Based Algorithms with Weighted Dynamic Time Warping Kernel Function for Time Series Classification}, author = {YS Jeong, R Jayaramam} } @misc{2014YSatoKKozukaYSawadaMKiyono, title = {Learning Multiple Complex Features Based on Classification Results}, author = {Y Sato, K Kozuka, Y Sawada, M Kiyono} } @misc{2014YShiaAKaratzogloubLBaltrunasbMLarsonc, title = {Cars2: Learning Context-aware Representations for Context-aware Recommendations}, author = {Y Shia, A Karatzogloub, L Baltrunasb, M Larsonc} } @misc{2014YSongDNiZZengLHeSChenBLeiTWang, title = {Automatic Vaginal Bacteria Segmentation and Classification Based on Superpixel and Deep Learning}, author = {Y Song, D Ni, Z Zeng, L He, S Chen, B Lei, T Wang} } @misc{2014YSunQLiuHLu, title = {Low rank driven robust facial landmark regression}, author = {Y Sun, Q Liu, H Lu} } @misc{2014YSunXWangXTang, title = {Deeply learned face representations are sparse, selective, and robust}, author = {Y Sun, X Wang, X Tang} } @misc{2014YTTsaiMCYeh, title = {Feature Selection And Extraction For Babyface Recognition}, author = {YT Tsai, MC Yeh} } @misc{2014YTaoHChenCQiu, title = {Wind Power Prediction and Pattern Feature Based on Deep Learning Method}, author = {Y Tao, H Chen, C Qiu} } @misc{2014YTianPLuoXWangXTang, title = {Pedestrian Detection aided by Deep Learning Semantic Tasks}, author = {Y Tian, P Luo, X Wang, X Tang} } @misc{2014YWangGWCottrell, title = {Bikers are like tobacco shops, formal dressers are like suits: Recognizing Urban Tribes with Caffe}, author = {Y Wang, GW Cottrell} } @misc{2014YWangJDuLDaiCHLee, title = {A fusion approach to spoken language identification based on combining multiple phone recognizers and speech attribute detectors}, author = {Y Wang, J Du, L Dai, CH Lee} } @misc{2014YWangSHu, title = {Exploiting high level feature for dynamic textures recognition}, author = {Y Wang, S Hu} } @misc{2014YWuQJi, title = {Discriminative Deep Face Shape Model for Facial Point Detection}, author = {Y Wu, Q Ji} } @misc{2014YXuJDuLRDaiCHLee, title = {Cross-language transfer learning for deep neural network based speech enhancement}, author = {Y Xu, J Du, LR Dai, CH Lee} } @misc{2014YYangJEisenstein, title = {Unsupervised Domain Adaptation with Feature Embeddings}, author = {Y Yang, J Eisenstein} } @misc{2014YYangYLiYAloimonos, title = {Robot Learning Manipulation Action Plans by â€œWatchingâ€ Unconstrained Videos from the World Wide Web}, author = {Y Yang, Y Li, Y Aloimonos} } @misc{2014YYinMJLiaoXLLi, title = {Pedestrian Detection Based on Multi-Stage Unsupervised Learning}, author = {Y Yin, MJ Liao, XL Li} } @misc{2014YZhangCShang, title = {Combining Newton interpolation and deep learning for image classification}, author = {Y Zhang, C Shang} } @misc{2014YZhangYChengKBJiaADZhang, title = {A generative model of identifying informative proteins from dynamic Ppi networks}, author = {Y Zhang, Y Cheng, KB Jia, AD Zhang} } @misc{2014YZhangZTangCZhangJLiuHLu, title = {Automatic face annotation in Tv series by video/script alignment}, author = {Y Zhang, Z Tang, C Zhang, J Liu, H Lu} } @misc{2014YZhaoJXueXChen, title = {Ensemble Learning Approaches in Speech Recognition}, author = {Y Zhao, J Xue, X Chen} } @misc{2014YZhengRSZemelYJZhangHLarochelle, title = {A Neural Autoregressive Approach to Attention-based Recognition}, author = {Y Zheng, RS Zemel, YJ Zhang, H Larochelle} } @misc{2014YZhengYJZhangHLarochelle, title = {A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data}, author = {Y Zheng, YJ Zhang, H Larochelle} } @misc{2014YZhuangZYuWWangFWuSTangJShao, title = {Cross-Media Hashing with Neural Networks}, author = {Y Zhuang, Z Yu, W Wang, F Wu, S Tang, J Shao} } @misc{2014ZAkataHLeeBSchiele, title = {Zero-Shot Learning with Structured Embeddings}, author = {Z Akata, H Lee, B Schiele} } @misc{2014ZBO, title = {A Biologically Inspired Human Posture Recognition System}, author = {Z BO} } @misc{2014ZCaoSLiYLiuWLiHJi, title = {A Novel Neural Topic Model and Its Supervised Extension}, author = {Z Cao, S Li, Y Liu, W Li, H Ji} } @misc{2014ZChenKYu, title = {An Investigation of Implementation and Performance Analysis of Dnn Based Speech Synthesis System}, author = {Z Chen, K Yu} } @misc{2014ZDaiADamianouJHensmanNLawrence, title = {Gaussian Process Models with Parallelization and Gpu acceleration}, author = {Z Dai, A Damianou, J Hensman, N Lawrence} } @misc{2014ZDongMPeiYHeTLiuYDongYJia, title = {Vehicle Type Classification Using Unsupervised Convolutional Neural Network}, author = {Z Dong, M Pei, Y He, T Liu, Y Dong, Y Jia} } @misc{2014ZDongYWuMPeiYJia, title = {Vehicle Type Classification Using Semi-Supervised Convolutional Neural Network}, author = {Z Dong, Y Wu, M Pei, Y Jia} } @misc{2014ZHuangMDongQMaoYZhan, title = {Speech Emotion Recognition Using Cnn}, author = {Z Huang, M Dong, Q Mao, Y Zhan} } @misc{2014ZJinJHuangWChengCYang, title = {A new algorithm on variable-rate convolutional broadcast for network coding in cyclic networks}, author = {Z Jin, J Huang, W Cheng, C Yang} } @misc{2014ZLiuCXieSBuXWangJHanHLinHZhang, title = {Indirect shape analysis for 3d shape retrieval}, author = {Z Liu, C Xie, S Bu, X Wang, J Han, H Lin, H Zhang} } @misc{2014ZLiuPLuoXWangXTang, title = {Deep Learning Face Attributes in the Wild}, author = {Z Liu, P Luo, X Wang, X Tang} } @misc{2014ZLiuQHuangJLiQWang, title = {Single image super-resolution via L0 image smoothing}, author = {Z Liu, Q Huang, J Li, Q Wang} } @misc{2014ZLiuQHuangJLiQWangSingleImageSuper-Resolution, title = {Single Image Super-Resolution via Image Smoothing}, author = {Z Liu, Q Huang, J Li, Q Wang} } @misc{2014ZLuAMayKLiuABGarakaniDGuoABelletLFan, title = {How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets}, author = {Z Lu, A May, K Liu, AB Garakani, D Guo, A Bellet, L Fan} } @misc{2014ZMaoCMaTHMHuangYChenYHuang, title = {Bimmer: a novel algorithm for detecting differential Dna methylation regions from MBDCap-seq data}, author = {Z Mao, C Ma, THM Huang, Y Chen, Y Huang} } @misc{2014ZShenXXue, title = {Do More Dropouts in Pool5 Feature Maps for Better Object Detection}, author = {Z Shen, X Xue} } @misc{2014ZWangJYangHJinEShechtmanAAgarwala, title = {Decomposition-Based Domain Adaptation for Real-World Font Recognition}, author = {Z Wang, J Yang, H Jin, E Shechtman, A Agarwala} } @misc{2014ZWuYHuangYYuLWangTTan, title = {Early Hierarchical Contexts Learned by Convolutional Networks for Image Segmentation}, author = {Z Wu, Y Huang, Y Yu, L Wang, T Tan} } @misc{2014ZWuYZhangFYuJXiao, title = {A Gpu Implementation of GoogLeNet}, author = {Z Wu, Y Zhang, F Yu, J Xiao} } @misc{2014ZWuZYuJYuanJZhang, title = {A twice face recognition algorithm}, author = {Z Wu, Z Yu, J Yuan, J Zhang} } @misc{2014ZYXuLNTangCPTian, title = {Prediction of Stock Trend Based on Deep Belief Networks}, author = {ZY Xu, LN Tang, CP Tian} } @misc{2014ZYanHZhangBWangSParisYYu, title = {Automatic Photo Adjustment Using Deep Learning}, author = {Z Yan, H Zhang, B Wang, S Paris, Y Yu} } @misc{2014ZYouBXu, title = {Improving training time of deep neural networkwith asynchronous averaged stochastic gradient descent}, author = {Z You, B Xu} } @misc{2014ZYouBXuInvestigationofstochastic, title = {Investigation of stochastic Hessian-Free optimization in Deep neural networks for speech recognition}, author = {Z You, B Xu} } @misc{2014ZZhangWZhangJLiuXTang, title = {Facial Landmark Localization using Hierarchical Pose Regression}, author = {Z Zhang, W Zhang, J Liu, X Tang} } @misc{2014ZZhouNChawlaYJinGWilliams, title = {Big Data Opportunities and Challenges: Discussions from Data Analytics Perspectives [Discussion Forum]}, author = {Z Zhou, N Chawla, Y Jin, G Williams} } @misc{2014ZZhuPLuoXWangXTang, title = {Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations}, author = {Z Zhu, P Luo, X Wang, X Tang} } @misc{2014ZZhuXWangSBaiCYaoXBai, title = {Deep Learning Representation using Autoencoder for 3d Shape Retrieval}, author = {Z Zhu, X Wang, S Bai, C Yao, X Bai} } @misc{2015AAshariSTatikondaMBoehmBReinwald, title = {On optimizing machine learning workloads via kernel fusion}, author = {A Ashari, S Tatikonda, M Boehm, B Reinwald} } @misc{2015ABadirZZeybekogluPKaracayNGÃ¶ktepeSTopcu, title = {Using High-fidelity Simulation as a Learning Strategy in an Undergraduate Intensive Care Course}, author = {A Badir, Z Zeybekoglu, P Karacay, N GÃ¶ktepe, S Topcu} } @misc{2015ABelletAHabrardMSebban, title = {Metric Learning}, author = {A Bellet, A Habrard, M Sebban} } @misc{2015ABuonannoFANPalmieri, title = {Towards Building Deep Networks with Bayesian Factor Graphs}, author = {A Buonanno, FAN Palmieri} } @misc{2015ACampbellVCiesielksiAKQin, title = {Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images}, author = {A Campbell, V Ciesielksi, AK Qin} } @misc{2015AElkahkyYSongXHe, title = {A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems}, author = {A Elkahky, Y Song, X He} } @misc{2015AGSchwingRUrtasun, title = {Fully Connected Deep Structured Networks}, author = {AG Schwing, R Urtasun} } @misc{2015AGangopadhyaySMTripathiIJindalSRaman, title = {Sa-cnn: Dynamic Scene Classification using Convolutional Neural Networks}, author = {A Gangopadhyay, SM Tripathi, I Jindal, S Raman} } @misc{2015AGkiokasAICristea, title = {Unsupervised neural controller for Reinforcement Learning action-selection: Learning to represent knowledge}, author = {A Gkiokas, AI Cristea} } @misc{2015AGkiokasEGTsardouliasPAMitkas, title = {Hive Collective Intelligence for Cloud Robotics: A Hybrid Distributed Robotic Controller Design for Learning and Adaptation}, author = {A Gkiokas, EG Tsardoulias, PA Mitkas} } @misc{2015AGorin, title = {Acoustic Model Structuring for Improving Automatic Speech Recognition Performance}, author = {A Gorin} } @misc{2015AJRSimpson, title = {Over-Sampling in a Deep Neural Network}, author = {AJR Simpson} } @misc{2015AJRSimpsonAbstractLearningvia, title = {Abstract Learning via Demodulation in a Deep Neural Network}, author = {AJR Simpson} } @misc{2015AJRSimpsonDeepTransform:Cocktail, title = {Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis}, author = {AJR Simpson} } @misc{2015AJRSimpsonDeepTransform:Error, title = {Deep Transform: Error Correction via Probabilistic Re-Synthesis}, author = {AJR Simpson} } @misc{2015AJRSimpsonDeepTransform:Time-Domain, title = {Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis}, author = {AJR Simpson} } @misc{2015AJoulinTMikolov, title = {Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets}, author = {A Joulin, T Mikolov} } @misc{2015ALacoste, title = {Agnostic Bayes}, author = {A Lacoste} } @misc{2015ALuWWangMBansalKGimpelKLivescu, title = {Deep Multilingual Correlation for Improved Word Embeddings}, author = {A Lu, W Wang, M Bansal, K Gimpel, K Livescu} } @misc{2015AMajumdar, title = {Real-time Dynamic Mri Reconstruction using Stacked Denoising Autoencoder}, author = {A Majumdar} } @misc{2015ANikfarjamASarkerKOConnorRGinnGGonzalez, title = {Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features}, author = {A Nikfarjam, A Sarker, K O'Connor, R Ginn, G Gonzalez} } @misc{2015APaulSVenkatasubramanian, title = {Why Does Unsupervised Deep Learning WORK?-Aperspective From Group Theory}, author = {A Paul, S Venkatasubramanian} } @misc{2015APayanGMontana, title = {Predicting Alzheimer's disease: a neuroimaging study with 3d convolutional neural networks}, author = {A Payan, G Montana} } @misc{2015APunjaniMABrubaker, title = {Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM}, author = {A Punjani, MA Brubaker} } @misc{2015ARaySRajeswarSChaudhury, title = {A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks}, author = {A Ray, S Rajeswar, S Chaudhury} } @misc{2015ARaySRajeswarSChaudhuryTextrecognitionusing, title = {Text recognition using deep Blstm networks}, author = {A Ray, S Rajeswar, S Chaudhury} } @misc{2015ASWebb, title = {Threshold concepts in the Scholarship of Teaching and Learning: a phenomenological study of educational leaders in a Canadian research-intensive university}, author = {AS Webb} } @misc{2015ASharmaOTuzelDWJacobs, title = {Deep Hierarchical Parsing for Semantic Segmentation}, author = {A Sharma, O Tuzel, DW Jacobs} } @misc{2015ASobhani, title = {P300 classification using deep belief nets}, author = {A Sobhani} } @misc{2015ASuzaniARasoulianASeitelSFelsRNRohling, title = {Deep learning for automatic localization, identification, and segmentation of vertebral bodies in volumetric Mr images}, author = {A Suzani, A Rasoulian, A Seitel, S Fels, RN Rohling} } @misc{2015ATorabiCPalHLarochelleACourville, title = {Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research}, author = {A Torabi, C Pal, H Larochelle, A Courville} } @misc{2015BChudasamaCDuvediJPThomas, title = {Learning facial expressions from an image}, author = {B Chudasama, C Duvedi, JP Thomas} } @misc{2015BGrahamJReizensteinLRobinson, title = {Efficient batchwise dropout training using submatrices}, author = {B Graham, J Reizenstein, L Robinson} } @misc{2015BKKhonglahBDSarmaSRMPrasanna, title = {Exploration of Deep Belief Networks for Vowel-like regions detection}, author = {BK Khonglah, BD Sarma, SRM Prasanna} } @misc{2015BKehoeSPatilPAbbeelKGoldberg, title = {A survey of research on cloud robotics and automation}, author = {B Kehoe, S Patil, P Abbeel, K Goldberg} } @misc{2015BLiaoJXuJLvSZhou, title = {An Image Retrieval Method for Binary Images Based on Dbn and Softmax Classifier}, author = {B Liao, J Xu, J Lv, S Zhou} } @misc{2015BLiuJFengMLiuHHuXWang, title = {Predicting the Quality of User-Generated Answers Using Co-Training in Community-based Question Answering Portals}, author = {B Liu, J Feng, M Liu, H Hu, X Wang} } @misc{2015BLiuJLiuHLu, title = {Detectionn guided deconvolutional network for hierarchical feature learning}, author = {B Liu, J Liu, H Lu} } @misc{2015BSafadiNDerbasAHamadiMBudnikPMulhem, title = {Lig at TRECVid 2014: Semantic Indexing}, author = {B Safadi, N Derbas, A Hamadi, M Budnik, P Mulhem} } @misc{2015BSchÃ¶lkopf, title = {Artificial intelligence: Learning to see and act}, author = {B SchÃ¶lkopf} } @misc{2015BWSchuller, title = {Modelling User Affect and Sentiment in Intelligent User Interfaces: A Tutorial Overview}, author = {BW Schuller} } @misc{2015BWilliamson, title = {Computing brains: neuroscience, machine intelligence and big data in the cognitive classroom}, author = {B Williamson} } @misc{2015BWuSLyuBGHuQJi, title = {Multi-label Learning with Missing Labels for Image Annotation and Facial Action Unit Recognition}, author = {B Wu, S Lyu, BG Hu, Q Ji} } @misc{2015BZhang, title = {Deep learning with application to hashing}, author = {B Zhang} } @misc{2015CCWangCHHuangCJLin, title = {Subsampled Hessian Newton Methods for Su-pervised Learning}, author = {CC Wang, CH Huang, CJ Lin} } @misc{2015CCaiYXuDKeKSu, title = {A Fast Learning Method for the Multi-layer Perceptron in Automatic Speech Recognition Systems}, author = {C Cai, Y Xu, D Ke, K Su} } @misc{2015CGulcehreOFiratKXuKChoLBarraultHCLin, title = {On Using Monolingual Corpora in Neural Machine Translation}, author = {C Gulcehre, O Firat, K Xu, K Cho, L Barrault, HC Lin} } @misc{2015CHazÄ±rbasJDieboldDCremers, title = {Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation}, author = {C HazÄ±rbas, J Diebold, D Cremers} } @misc{2015CLChenCYZhangLChenMGan, title = {Fuzzy Restricted Boltzmann Machine and Its Fast Learning Algorithm}, author = {CL Chen, CY Zhang, L Chen, M Gan} } @misc{2015CMaCLiu, title = {Two Dimensional Hashing for Visual Tracking}, author = {C Ma, C Liu} } @misc{2015CSagonasYPanagakisSZafeiriouMPantic, title = {Face frontalization for Alignment and Recognition}, author = {C Sagonas, Y Panagakis, S Zafeiriou, M Pantic} } @misc{2015CWDengGBHuangJXuJXTang, title = {Extreme learning machines: new trends and applications}, author = {CW Deng, GB Huang, J Xu, JX Tang} } @misc{2015CXiongLLiuXZhaoSYanTKKim, title = {Convolutional Fusion Network for Face Verification in the Wild}, author = {C Xiong, L Liu, X Zhao, S Yan, TK Kim} } @misc{2015CYTsaiDDCox, title = {Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework}, author = {CY Tsai, DD Cox} } @misc{2015CZhangJChengYZhangJLiuCLiangJPang, title = {Image classification using boosted local features with random orientation and location selection}, author = {C Zhang, J Cheng, Y Zhang, J Liu, C Liang, J Pang} } @misc{2015CZhangPLiGSunYGuanBXiaoJCong, title = {Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks}, author = {C Zhang, P Li, G Sun, Y Guan, B Xiao, J Cong} } @misc{2015CZhongDKaramshukNSastry, title = {Predicting Pinterest: Automating a distributed human computation}, author = {C Zhong, D Karamshuk, N Sastry} } @misc{2015DAClevertTUnterthinerAMayrHRamsauer, title = {Rectified Factor Networks}, author = {DA Clevert, T Unterthiner, A Mayr, H Ramsauer} } @misc{2015DCarlsonVCevherLCarin, title = {Stochastic Spectral Descent for Restricted Boltzmann Machines}, author = {D Carlson, V Cevher, L Carin} } @misc{2015DChengJWangXWeiNLiuSZhangYGong, title = {Cascade object detection with complementary features and algorithms}, author = {D Cheng, J Wang, X Wei, N Liu, S Zhang, Y Gong} } @misc{2015DCorneMDissanayakeAPeacockSGalloway, title = {Accurate localized short term weather prediction for renewables planning}, author = {D Corne, M Dissanayake, A Peacock, S Galloway} } @misc{2015DDaiRTimofteLVanGool, title = {Jointly Optimized Regressors for Image Super-resolution}, author = {D Dai, R Timofte, L Van Gool} } @misc{2015DEWrightSJSmarttKWSmithPMillerRKotak, title = {Machine learning for transient discovery in Pan-STARRS1 difference imaging}, author = {DE Wright, SJ Smartt, KW Smith, P Miller, R Kotak} } @misc{2015DGhadiyaramABovik, title = {Electronic Imaging & Signal Processing Automatic quality prediction of authentically distorted pictures}, author = {D Ghadiyaram, A Bovik} } @misc{2015DGhadiyaramABovikFeaturemapsdriven, title = {Feature maps driven no-reference image quality prediction of authentically distorted images}, author = {D Ghadiyaram, A Bovik} } @misc{2015DHPhanTDCao, title = {Applying skip-gram word estimation and SVM-based classification for opinion mining Vietnamese food places text reviews}, author = {DH Phan, TD Cao} } @misc{2015DHadfieldMenellAXLeeCFinnETzengSHuang, title = {Beyond Lowest-Warping Cost Action Selection in Trajectory Transfer}, author = {D Hadfield-Menell, AX Lee, C Finn, E Tzeng, S Huang} } @misc{2015DJCookNCKrishnan, title = {Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data}, author = {DJ Cook, NC Krishnan} } @misc{2015DLiYTianHXu, title = {Deep Twin Support Vector Machine}, author = {D Li, Y Tian, H Xu} } @misc{2015DMaclaurinDDuvenaudRPAdams, title = {Gradient-based Hyperparameter Optimization through Reversible Learning}, author = {D Maclaurin, D Duvenaud, RP Adams} } @misc{2015DMaturanaSScherer, title = {3d Convolutional Neural Networks for Landing Zone Detection from LiDAR}, author = {D Maturana, S Scherer} } @misc{2015DMenottiGChiachiaAPintoWSchwartzHPedrini, title = {Deep Representations for Iris, Face, and Fingerprint Spoofing Detection}, author = {D Menotti, G Chiachia, A Pinto, W Schwartz, H Pedrini} } @misc{2015DMeyerRDegenneAOmraneHShen, title = {Accelerated gradient temporal difference learning algorithms}, author = {D Meyer, R Degenne, A Omrane, H Shen} } @misc{2015DPGuralnikDEKoditschek, title = {Universal Memory Architectures for Autonomous Machines}, author = {DP Guralnik, DE Koditschek} } @misc{2015DSejdinovic, title = {Hypothesis Testing with Kernel Embeddings on Big and Interdependent Data}, author = {D Sejdinovic} } @misc{2015DTuiaRFlamaryNCourty, title = {Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions}, author = {D Tuia, R Flamary, N Courty} } @misc{2015EDernerTSvoboda, title = {Indexing Images for Visual Memory by Using Dnn Descriptorsâ€“Preliminary Experiments}, author = {E Derner, T Svoboda} } @misc{2015EHazanKYLevySShalevSwartz, title = {On Graduated Optimization for Stochastic Non-Convex Problems}, author = {E Hazan, KY Levy, S Shalev-Swartz} } @misc{2015EMFedrianiMChavesMaza, title = {Entrepreneurship Support Based on Mixed Bio-Artificial Neural Network Simulator (esbbann)}, author = {EM Fedriani, M Chaves-Maza} } @misc{2015EPIjjinaCKMohan, title = {Human Action Recognition Based on Recognition of Linear Patterns in Action Bank Features Using Convolutional Neural Networks}, author = {EP Ijjina, CK Mohan} } @misc{2015EZhouZCaoQYin, title = {Naive-Deep Face Recognition: Touching the Limit of Lfw Benchmark or Not?}, author = {E Zhou, Z Cao, Q Yin} } @misc{2015FAnselmiLRosascoTPoggio, title = {On Invariance and Selectivity in Representation Learning}, author = {F Anselmi, L Rosasco, T Poggio} } @misc{2015FContiLBenini, title = {A Ultra-Low-Energy Convolution Engine for Fast Brain-Inspired Vision in Multicore Clusters}, author = {F Conti, L Benini} } @misc{2015FDiehlAJauch, title = {apsis-Framework for Automated Optimization of Machine Learning Hyper Parameters}, author = {F Diehl, A Jauch} } @misc{2015FLiuCShenGLinIReid, title = {Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields}, author = {F Liu, C Shen, G Lin, I Reid} } @misc{2015FSchroffDKalenichenkoJPhilbin, title = {FaceNet: A Unified Embedding for Face Recognition and Clustering}, author = {F Schroff, D Kalenichenko, J Philbin} } @misc{2015GAcamporaPFoggiaASaggeseMVento, title = {A Hierarchical Neuro-Fuzzy Architecture for Human Behavior Analysis}, author = {G Acampora, P Foggia, A Saggese, M Vento} } @misc{2015GAlainYBengioLYaoJYosinski, title = {GSNs: Generative Stochastic Networks}, author = {G Alain, Y Bengio, L Yao, J Yosinski} } @misc{2015GBRonsivalleSCartaVMetusMOrlando, title = {Neuraledugaming: A Mathematical â€œBrainâ€ to Make Digital Edugames Smart}, author = {GB Ronsivalle, S Carta, V Metus, M Orlando} } @misc{2015GChen, title = {Deep Learning with Nonparametric Clustering}, author = {G Chen} } @misc{2015GCybenko, title = {Deep Learning of Behaviors for Security}, author = {G Cybenko} } @misc{2015GFerroniRBonfigliEPrincipiSSquartiniFPiazza, title = {Neural Networks Based Methods for Voice Activity Detection in a Multi-room Domestic Environment}, author = {G Ferroni, R Bonfigli, E Principi, S Squartini, F Piazza} } @misc{2015GKejelaRMEstevesCRong, title = {Predictive Analytics of Sensor Data Using Distributed Machine Learning Techniques}, author = {G Kejela, RM Esteves, C Rong} } @misc{2015GOrchardCMeyerREtienneCummingsCPosch, title = {HFirst: A Temporal Approach to Object Recognition}, author = {G Orchard, C Meyer, R Etienne-Cummings, C Posch} } @misc{2015GPapandreouLCChenKMurphyALYuille, title = {Weakly-and Semi-Supervised Learning of a Dcnn for Semantic Image Segmentation}, author = {G Papandreou, LC Chen, K Murphy, AL Yuille} } @misc{2015HAramoImmonenJJussilaJHuhtamÃ¤ki, title = {Exploring co-learning behavior of conference participants with visual network analysis of Twitter data}, author = {H Aramo-Immonen, J Jussila, J HuhtamÃ¤ki} } @misc{2015HForoughiNRayHZhang, title = {Robust people counting using sparse representation and random projection}, author = {H Foroughi, N Ray, H Zhang} } @misc{2015HHuangTToyoizumi, title = {Advanced Mean Field Theory of Restricted Boltzmann Machine}, author = {H Huang, T Toyoizumi} } @misc{2015HKangJHaJShinHGLeeYWang, title = {Unsupervised Incremental Learning of Associative Cubes with Orthogonal Kernels}, author = {H Kang, J Ha, J Shin, HG Lee, Y Wang} } @misc{2015HLiYLiFPorikli, title = {DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking}, author = {H Li, Y Li, F Porikli} } @misc{2015HLobelRVidalASoto, title = {Learning Shared, Discriminative, and Compact Representations for Visual Recognition}, author = {H Lobel, R Vidal, A Soto} } @misc{2015HManoBSeymour, title = {Pain: a distributed brain information network?}, author = {H Mano, B Seymour} } @misc{2015HPalangiLDengYShenJGaoXHeJChen, title = {Deep Sentence Embedding Using the Long Short Term Memory Network: Analysis and Application to Information Retrieval}, author = {H Palangi, L Deng, Y Shen, J Gao, X He, J Chen} } @misc{2015HRRothAFaragLLuEBTurkbeyRMSummers, title = {Deep convolutional networks for pancreas segmentation in Ct imaging}, author = {HR Roth, A Farag, L Lu, EB Turkbey, RM Summers} } @misc{2015HSchaferJRaabBKeinertMMeyerMStamminger, title = {Dynamic Feature-Adaptive Subdivision}, author = {H Schafer, J Raab, B Keinert, M Meyer, M Stamminger} } @misc{2015HSunHMaWYihCTTsaiJLiuMWChang, title = {Open Domain Question Answering via Semantic Enrichment}, author = {H Sun, H Ma, W Yih, CT Tsai, J Liu, MW Chang} } @misc{2015HWuXZhangLZhangXZou, title = {Speech Separation based on Deep Belief Network}, author = {H Wu, X Zhang, L Zhang, X Zou} } @misc{2015HZenHSak, title = {Unidirectional Long Short-term Memory Recurrent Neural Network With Recurrent Output Layer For Low-latency Speech â€¦}, author = {H Zen, H Sak} } @misc{2015HZhangYLiuBXieJYu, title = {Spatially Constrained Sparse Coding Scheme for Natural Scene Categorization}, author = {H Zhang, Y Liu, B Xie, J Yu} } @misc{2015IArnaldoKVeeramachaneniASongUOReilly, title = {Bring Your Own Learner: A Cloud-Based, Data-Parallel Commons for Machine Learning}, author = {I Arnaldo, K Veeramachaneni, A Song, U O'Reilly} } @misc{2015IGoodfellow, title = {Deep learning of representations and its application to computer vision}, author = {I Goodfellow} } @misc{2015IHongKBongDShinSParkKLeeYKimHJYoo, title = {18.1 A 2.71 nJ/pixel 3D-stacked gaze-activated object-recognition system for low-power mobile Hmd applications}, author = {I Hong, K Bong, D Shin, S Park, K Lee, Y Kim, HJ Yoo} } @misc{2015IPotamitis, title = {Unsupervised dictionary extraction of bird vocalizations and new tools on assessing and visualizing bird activity}, author = {I Potamitis} } @misc{2015JAHendersonTTAGibsonJWiles, title = {Spike Event Based Learning in Neural Networks}, author = {JA Henderson, TTA Gibson, J Wiles} } @misc{2015JAMiÃ±arroGimÃ©nezOMarÃnAlonsoMSamwald, title = {Applying deep learning techniques on medical corpora from the World Wide Web: a prototypical system and evaluation}, author = {JA MiÃ±arro-GimÃ©nez, O MarÃn-Alonso, M Samwald} } @misc{2015JBaiYWuJZhangFChen, title = {Subset based deep learning for Rgb-d object recognition}, author = {J Bai, Y Wu, J Zhang, F Chen} } @misc{2015JBrunaSChintalaYLeCunSPiantinoASzlam, title = {A theoretical argument for complex-valued convolutional networks}, author = {J Bruna, S Chintala, Y LeCun, S Piantino, A Szlam} } @misc{2015JDaiKHeJSun, title = {BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation}, author = {J Dai, K He, J Sun} } @misc{2015JEslavaRios, title = {Automatic melanoma detection in dermatological images}, author = {J Eslava Rios} } @misc{2015JGaoXHeLDeng, title = {Deep Learning for Web Search and Natural Language Processing}, author = {J Gao, X He, L Deng} } @misc{2015JGauthier, title = {Conditional generative adversarial nets for convolutional face generation}, author = {J Gauthier} } @misc{2015JGirardMREmami, title = {Robot team learning enhancement using Human Advice}, author = {J Girard, MR Emami} } @misc{2015JHanDZhangSWenLGuoTLiuXLi, title = {Two-Stage Learning to Predict Human Eye Fixations via SDAEs}, author = {J Han, D Zhang, S Wen, L Guo, T Liu, X Li} } @misc{2015JHeaton, title = {Replicating the Research of the Paper:â€œApplication of Artificial Neural Network in Detection of Probing Attacksâ€}, author = {J Heaton} } @misc{2015JHosangMOmranRBenensonBSchiele, title = {Taking a Deeper Look at Pedestrians}, author = {J Hosang, M Omran, R Benenson, B Schiele} } @misc{2015JIbarzYBulatovIGoodfellow, title = {Sequence transcription with deep neural networks}, author = {J Ibarz, Y Bulatov, I Goodfellow} } @misc{2015JJohnsonZJiangMYanez, title = {DigiRec Proposal: Handwritten Digit Recognition in Hardware}, author = {J Johnson, Z Jiang, M Yanez} } @misc{2015JKDuttaBBanerjee, title = {Learning features and their transformations from natural videos}, author = {JK Dutta, B Banerjee} } @misc{2015JKONGKSUNMJIANGHHUOAYIMING, title = {The Improvement of Structured-output Regression Forests on Detection about Face Partsâ‹†}, author = {J KONG, K SUN, M JIANG, H HUO, A YIMING} } @misc{2015JKarhunenTRaikoKHCho, title = {Unsupervised Deep Learning: A Short Review}, author = {J Karhunen, T Raiko, KH Cho} } @misc{2015JKuenKMLimCPLee, title = {Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle}, author = {J Kuen, KM Lim, CP Lee} } @misc{2015JLiDJurafskyEHovy, title = {When Are Tree Structures Necessary for Deep Learning of Representations?}, author = {J Li, D Jurafsky, E Hovy} } @misc{2015JLiangKKelly, title = {Training Stacked Denoising Autoencoders for Representation Learning}, author = {J Liang, K Kelly} } @misc{2015JLinOMorereVChandrasekharAVeillardHGoh, title = {DeepHash: Getting Regularization, Depth and Fine-Tuning Right}, author = {J Lin, O Morere, V Chandrasekhar, A Veillard, H Goh} } @misc{2015JLiuKZhaoBKusyJWenRJurdak, title = {Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets}, author = {J Liu, K Zhao, B Kusy, J Wen, R Jurdak} } @misc{2015JLuVBehboodPHaoHZuoSXueGZhang, title = {Transfer Learning using Computational Intelligence: A Survey}, author = {J Lu, V Behbood, P Hao, H Zuo, S Xue, G Zhang} } @misc{2015JLuVELiongXZhouJZhou, title = {Learning Compact Binary Face Descriptor for Face Recognition}, author = {J Lu, VE Liong, X Zhou, J Zhou} } @misc{2015JMaRPSheridanALiawGDahlVSvetnik, title = {Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships}, author = {J Ma, RP Sheridan, A Liaw, G Dahl, V Svetnik} } @misc{2015JMansanetAAlbiolRParedesAAlbiol, title = {Mask selective regularization for restricted Boltzmann machines}, author = {J Mansanet, A Albiol, R Paredes, A Albiol} } @misc{2015JMartensRGrosse, title = {Optimizing Neural Networks with Kronecker-factored Approximate Curvature}, author = {J Martens, R Grosse} } @misc{2015JPadmanabhanMJJohnsonPremkumar, title = {Machine Learning in Automatic Speech Recognition: A Survey}, author = {J Padmanabhan, MJ Johnson Premkumar} } @misc{2015JSnoekORippelKSwerskyRKirosNSatish, title = {Scalable Bayesian Optimization Using Deep Neural Networks}, author = {J Snoek, O Rippel, K Swersky, R Kiros, N Satish} } @misc{2015JSohlDicksteinEAWeissNMaheswaranathan, title = {Deep Unsupervised Learning using Nonequilibrium Thermodynamics}, author = {J Sohl-Dickstein, EA Weiss, N Maheswaranathan} } @misc{2015JSunWCaoZXuJPonce, title = {Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal}, author = {J Sun, W Cao, Z Xu, J Ponce} } @misc{2015JTayyubATavanaiYGatsoulisAGCohnDCHogg, title = {Qualitative and Quantitative Spatio-Temporal Relations in Daily Living Activity Recognition}, author = {J Tayyub, A Tavanai, Y Gatsoulis, AG Cohn, DC Hogg} } @misc{2015JWHaKMKimBTZhang, title = {Automated Construction of Visual-Linguistic Knowledge via Concept Learning from Cartoon Videos}, author = {JW Ha, KM Kim, BT Zhang} } @misc{2015JWeng, title = {Brain as an Emergent Finite Automaton: A Theory and Three Theorems}, author = {J Weng} } @misc{2015JYoungNHawes, title = {Learning by Observation Using Qualitative Spatial Relations}, author = {J Young, N Hawes} } @misc{2015JZhangSNguyenYShangDXuIKosztin, title = {Fast loop modeling for protein structures}, author = {J Zhang, S Nguyen, Y Shang, D Xu, I Kosztin} } @misc{2015JvandeWeijerFSKhan, title = {An Overview of Color Name Applications in Computer Vision}, author = {J van de Weijer, FS Khan} } @misc{2015KGregorIDanihelkaAGravesDWierstra, title = {Draw: A Recurrent Neural Network For Image Generation}, author = {K Gregor, I Danihelka, A Graves, D Wierstra} } @misc{2015KHLauYHTayFLLo, title = {A Hmax with Llc for visual recognition}, author = {KH Lau, YH Tay, FL Lo} } @misc{2015KHeXZhangSRenJSun, title = {Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification}, author = {K He, X Zhang, S Ren, J Sun} } @misc{2015KLiGQiJYeKAHua, title = {Rank Subspace Learning for Compact Hash Codes}, author = {K Li, G Qi, J Ye, KA Hua} } @misc{2015KMiuraTHarada, title = {Implementation of a Practical Distributed Calculation System with Browsers and JavaScript, and Application to Distributed Deep Learning}, author = {K Miura, T Harada} } @misc{2015KNiRPearceKBoakyeBVanEssenDBorth, title = {Large-Scale Deep Learning on the Yfcc100m Dataset}, author = {K Ni, R Pearce, K Boakye, B Van Essen, D Borth} } @misc{2015KSelyuninDRatasichEBartocciRGrosu, title = {Deep Neural Programs for Adaptive Control in Cyber-Physical Systems}, author = {K Selyunin, D Ratasich, E Bartocci, R Grosu} } @misc{2015KXuJBaRKirosACourvilleRSalakhutdinov, title = {Show, Attend and Tell: Neural Image Caption Generation with Visual Attention}, author = {K Xu, J Ba, R Kiros, A Courville, R Salakhutdinov} } @misc{2015KZhangQLiuYWuMHYang, title = {Robust Tracking via Convolutional Networks without Learning}, author = {K Zhang, Q Liu, Y Wu, MH Yang} } @misc{2015LAJeniJFCohnTKanade, title = {Dense 3d Face Alignment from 2d Videos in Real-Time}, author = {LA Jeni, JF Cohn, T Kanade} } @misc{2015LEBeerKRodriguezCTaylorNMartinezJones, title = {Awareness, Integration and Interconnectedness Contemplative Practices of Higher Education Professionals}, author = {LE Beer, K Rodriguez, C Taylor, N Martinez-Jones} } @misc{2015LJDengWGuoTZHuang, title = {Single image super-resolution by approximated Heaviside functions}, author = {LJ Deng, W Guo, TZ Huang} } @misc{2015LLWangNHCYung, title = {Hybrid Graphical Model for Semantic Image Segmentation}, author = {LL Wang, NHC Yung} } @misc{2015LLiu, title = {Learning Discriminative Feature Representations for Visual Categorization}, author = {L Liu} } @misc{2015LLiuLShaoXLiKLu, title = {Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach}, author = {L Liu, L Shao, X Li, K Lu} } @misc{2015LMcAfeeKOlukotun, title = {Emeuro: a framework for generating multi-purpose accelerators via deep learning}, author = {L McAfee, K Olukotun} } @misc{2015LPigouSDielemanPJKindermansBSchrauwen, title = {Sign language recognition using convolutional neural networks}, author = {L Pigou, S Dieleman, PJ Kindermans, B Schrauwen} } @misc{2015LYaoATorabiKChoNBallasCPalHLarochelle, title = {Video Description Generation Incorporating Spatio-Temporal Features and a Soft-Attention Mechanism}, author = {L Yao, A Torabi, K Cho, N Ballas, C Pal, H Larochelle} } @misc{2015LZhangLLinXWuSDingLZhang, title = {End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning}, author = {L Zhang, L Lin, X Wu, S Ding, L Zhang} } @misc{2015LZhengKIdrissiCGarciaSDuffnerABaskurt, title = {Logistic Similarity Metric Learning For Face Verification}, author = {L Zheng, K Idrissi, C Garcia, S Duffner, A Baskurt} } @misc{2015MAlber, title = {Masterarbeit: Big Data and Machine Learning: A Case Study with Bump Boost}, author = {M Alber} } @misc{2015MAslanASengurYXiaoHWangMCInceXMa, title = {Shape Feature Encoding via Fisher Vector for Efficient Fall Detection in Depth-Videos}, author = {M Aslan, A Sengur, Y Xiao, H Wang, MC Ince, X Ma} } @misc{2015MBackstromDCOOPER, title = {'Hiring a Nashville sensation': using narrative learning to develop the problem solving skills of contract law students}, author = {M Backstrom, D COOPER} } @misc{2015MCicconetDGeigerMWerman, title = {Complex-Valued Hough Transforms for Circles}, author = {M Cicconet, D Geiger, M Werman} } @misc{2015MDobrotaMVujoÅ¡eviÄ‡, title = {Forecasting And Inventory Performance In Direct-store Delivery Supply Chain: Case Of Retailer In Serbia}, author = {M Dobrota, M VujoÅ¡eviÄ‡} } @misc{2015MGermainKGregorIMurrayHLarochelle, title = {Made: Masked Autoencoder for Distribution Estimation}, author = {M Germain, K Gregor, I Murray, H Larochelle} } @misc{2015MGheisariMSBaghshah, title = {Unsupervised domain adaptation via representation learning and adaptive classifier learning}, author = {M Gheisari, MS Baghshah} } @misc{2015MHaloi, title = {A novel pLSA based Traffic Signs Classification System}, author = {M Haloi} } @misc{2015MHermansMSorianoJDambrePBienstman, title = {Photonic Delay Systems as Machine Learning Implementations}, author = {M Hermans, M Soriano, J Dambre, P Bienstman} } @misc{2015MHirnNPoilvertSMallat, title = {Quantum Energy Regression using Scattering Transforms}, author = {M Hirn, N Poilvert, S Mallat} } @misc{2015MKharratzadehTRShultz, title = {Neural Implementation of Probabilistic Models of Cognition}, author = {M Kharratzadeh, TR Shultz} } @misc{2015MKimLRigazio, title = {Deep Clustered Convolutional Kernels}, author = {M Kim, L Rigazio} } @misc{2015MKÃ¤cheleMGlodekDZharkovSMeudt, title = {Fusion of audio-visual features using hierarchical classifier systems for the recognition of affective states and the state of depression}, author = {M KÃ¤chele, M Glodek, D Zharkov, S Meudt} } @misc{2015MLessmannRPWÃ¼rtz, title = {Learning invariant object recognition from temporal correlation in a hierarchical network}, author = {M Lessmann, RP WÃ¼rtz} } @misc{2015MMNajafabadiFVillanustreTMKhoshgoftaar, title = {Deep learning applications and challenges in big data analytics}, author = {MM Najafabadi, F Villanustre, TM Khoshgoftaar} } @misc{2015MMSaleem, title = {Deep learning for speech classification and speaker recognition}, author = {MM Saleem} } @misc{2015MNStolarMLechISBurnett, title = {Optimized multi-channel deep neural network with 2d graphical representation of acoustic speech features for emotion recognition}, author = {MN Stolar, M Lech, IS Burnett} } @misc{2015MOYahaya, title = {On the Problem of Features Variability in Sequence Learning Problems}, author = {MO Yahaya} } @misc{2015MOberwegerPWohlhartVLepetit, title = {Hands Deep in Deep Learning for Hand Pose Estimation}, author = {M Oberweger, P Wohlhart, V Lepetit} } @misc{2015MOhzeki, title = {Statistical-mechanical analysis of pre-training and fine tuning in deep learning}, author = {M Ohzeki} } @misc{2015MOhzekiL_1-regularizedBoltzmannmachine, title = {L_1-regularized Boltzmann machine learning using majorizer minimization}, author = {M Ohzeki} } @misc{2015MPeemenBMesmanHCorporaal, title = {A Data-Reuse Aware Accelerator for Large-Scale Convolutional Networks}, author = {M Peemen, B Mesman, H Corporaal} } @misc{2015MPeemenBMesmanHCorporaalInter-TileReuseOptimization, title = {Inter-Tile Reuse Optimization Applied to Bandwidth Constrained Embedded Accelerators}, author = {M Peemen, B Mesman, H Corporaal} } @misc{2015MProbst, title = {Denoising Autoencoders for fast Combinatorial Black Box Optimization}, author = {M Probst} } @misc{2015MRashwanAAlSallabHMRaafatARafea, title = {Deep Learning Framework with Confused Sub-Set Resolution Architecture for Automatic Arabic Diacritization}, author = {M Rashwan, A Al Sallab, HM Raafat, A Rafea} } @misc{2015MSGashlerZKindle, title = {A Minimal Architecture for General Cognition}, author = {MS Gashler, Z Kindle} } @misc{2015MSahasrabudhe, title = {Fingerprint Image Enhancement Using Unsupervised Hierarchical Feature Learning}, author = {M Sahasrabudhe} } @misc{2015MSongZSunKLiuXLang, title = {Iterative 3d shape classification by online metric learning}, author = {M Song, Z Sun, K Liu, X Lang} } @misc{2015MThom, title = {Sparse Neural Networks}, author = {M Thom} } @misc{2015MUzairFShafaitBGhanemAMian, title = {Representation Learning with Deep Extreme Learning Machines for Efficient Image Set Classification}, author = {M Uzair, F Shafait, B Ghanem, A Mian} } @misc{2015MWangZLuHLiQLiu, title = {Syntax-based Deep Matching of Short Texts}, author = {M Wang, Z Lu, H Li, Q Liu} } @misc{2015MWeinmannBJutziSHinzCMallet, title = {Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers}, author = {M Weinmann, B Jutzi, S Hinz, C Mallet} } @misc{2015MYLiuAMallyaOCTuzelXChen, title = {Unsupervised Deep Network Pretraining via Human Design}, author = {MY Liu, A Mallya, OC Tuzel, X Chen} } @misc{2015MYasuda, title = {Monte Carlo Integration Using Spatial Structure of Markov Random Field}, author = {M Yasuda} } @misc{2015MZhou, title = {Entity-centric search: querying by entities and for entities}, author = {M Zhou} } @misc{2015NJieBXiongzhuLZhongWYao, title = {An Improved Bilinear Deep Belief Network Algorithm for Image Classification}, author = {N Jie, B Xiongzhu, L Zhong, W Yao} } @misc{2015NJojicAPerinaDKim, title = {Hierarchical learning of grids of microtopics}, author = {N Jojic, A Perina, D Kim} } @misc{2015NKarnaISuwardiNMaulidevi, title = {Knowledge Representation for Image Feature Extraction}, author = {N Karna, I Suwardi, N Maulidevi} } @misc{2015NNguyenAYoshitaka, title = {Human Interaction Recognition Using Independent Subspace Analysis Algorithm}, author = {N Nguyen, A Yoshitaka} } @misc{2015NTishbyNZaslavsky, title = {Deep Learning and the Information Bottleneck Principle}, author = {N Tishby, N Zaslavsky} } @misc{2015NWangSLiAGuptaDYYeung, title = {Transferring Rich Feature Hierarchies for Robust Visual Tracking}, author = {N Wang, S Li, A Gupta, DY Yeung} } @misc{2015NYHammerlaJMFisherPAndrasLRochester, title = {Pd Disease State Assessment in Naturalistic Environments using Deep Learning}, author = {NY Hammerla, JM Fisher, P Andras, L Rochester} } @misc{2015OLemonAEshghi, title = {Deep Reinforcement Learning for constructing meaning by 'babbling'}, author = {O Lemon, A Eshghi} } @misc{2015OMorÃ¨reHGohAVeillardVChandrasekharJLin, title = {Co-Regularized Deep Representations for Video Summarization}, author = {O MorÃ¨re, H Goh, A Veillard, V Chandrasekhar, J Lin} } @misc{2015OYAlJarrahPDYooSMuhaidatGKKaragiannidis, title = {Efficient Machine Learning for Big Data: A Review}, author = {OY Al-Jarrah, PD Yoo, S Muhaidat, GK Karagiannidis} } @misc{2015PAgarwalAKumar, title = {Predicting ocean health, one plankton at a time}, author = {P Agarwal, A Kumar} } @misc{2015PBaldiPSadowskiDWhiteson, title = {Enhanced Higgs Boson to Ï„+ Ï„âˆ’ Search with Deep Learning}, author = {P Baldi, P Sadowski, D Whiteson} } @misc{2015PHuangXHeJGaoLDengAAceroLPHeck, title = {Deep Structured Semantic Model Produced Using Click-Through Data}, author = {P Huang, X He, J Gao, L Deng, A Acero, LP Heck} } @misc{2015PHuberZHFengWChristmasJKittlerMRÃ¤tsch, title = {Fitting 3d Morphable Models using Local Features}, author = {P Huber, ZH Feng, W Christmas, J Kittler, M RÃ¤tsch} } @misc{2015PKuhadAYassineSShirmohammadi, title = {Using Distance Estimation and Deep Learning to Simplify Calibration in Food Calorie Measurement}, author = {P Kuhad, A Yassine, S Shirmohammadi} } @misc{2015PLeWZuidema, title = {Compositional Distributional Semantics with Long Short Term Memory}, author = {P Le, W Zuidema} } @misc{2015PSHuangMKimMHasegawaJohnson, title = {Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation}, author = {PS Huang, M Kim, M Hasegawa-Johnson} } @misc{2015PSSattigeri, title = {Exploring Latent Structure in Data: Algorithms and Implementations}, author = {PS Sattigeri} } @misc{2015PSinghAVermaNSChaudhari, title = {On the Performance Improvement of Devanagri Handwritten Character Recognition}, author = {P Singh, A Verma, NS Chaudhari} } @misc{2015PVerbancsicsJHarguess, title = {Image Classification Using Generative Neuro Evolution for Deep Learning}, author = {P Verbancsics, J Harguess} } @misc{2015PWangWLiZGaoJZhangCTangPOgunbona, title = {Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences}, author = {P Wang, W Li, Z Gao, J Zhang, C Tang, P Ogunbona} } @misc{2015PWohlhartVLepetit, title = {Learning Descriptors for Object Recognition and 3d Pose Estimation}, author = {P Wohlhart, V Lepetit} } @misc{2015QBNguyenTTVuCMLuong, title = {Improving acoustic model for English Asr System using deep neural network}, author = {QB Nguyen, TT Vu, CM Luong} } @misc{2015QLvYDouXNiuJXuJXuFXia, title = {Urban Land Use and Land Cover Classification Using Remotely Sensed Sar Data through Deep Belief Networks}, author = {Q Lv, Y Dou, X Niu, J Xu, J Xu, F Xia} } @misc{2015QMaITanigawaMMurata, title = {Retrieval Term Prediction Using Deep Belief Networks}, author = {Q Ma, I Tanigawa, M Murata} } @misc{2015QWangJFangYYuan, title = {Adaptive Road Detection via Context-aware Label Transfer}, author = {Q Wang, J Fang, Y Yuan} } @misc{2015RAManapLShao, title = {Non-Distortion-Specific no-reference image quality assessment: A survey}, author = {RA Manap, L Shao} } @misc{2015RBahgat, title = {Utilizing Deep Learning for Content-based Community Detection}, author = {R Bahgat} } @misc{2015RBruecknerBSchuller, title = {Be at Odds? Deep and Hierarchical Neural Networks for Classification and Regression of Conflict in Speech}, author = {R Brueckner, B Schuller} } @misc{2015RFuJGuoBQinWCheHWangTLiu, title = {Learning Semantic Hierarchies: A Continuous Vector Space Approach}, author = {R Fu, J Guo, B Qin, W Che, H Wang, T Liu} } @misc{2015RGopalanRLiVMPatelRChellappa, title = {Domain Adaptation for Visual Recognition}, author = {R Gopalan, R Li, VM Patel, R Chellappa} } @misc{2015RKSarvadevabhatlaRVBabu, title = {Freehand Sketch Recognition Using Deep Features}, author = {RK Sarvadevabhatla, RV Babu} } @misc{2015RKamimura, title = {Explicit knowledge extraction in information-theoretic supervised multi-layered Som}, author = {R Kamimura} } @misc{2015RMCCOPPIN, title = {An Evolutionary Approximation to Contrastive Divergence in Convolutional Restricted Boltzmann Machines}, author = {R MCCOPPIN} } @misc{2015RSkynerJMcDonaghCRGroomTvanMourik, title = {A Review of Methods for the Calculation of Solution Free Energies and the Modelling of Systems in Solution}, author = {R Skyner, J McDonagh, CR Groom, T van Mourik} } @misc{2015RWuSYanYShanQDangGSun, title = {Deep Image: Scaling up Image Recognition}, author = {R Wu, S Yan, Y Shan, Q Dang, G Sun} } @misc{2015SAnandaYogendran, title = {Method and System for Predicting Spatial and Temporal Distributions of Therapeutic Substance Carriers}, author = {S Ananda Yogendran} } @misc{2015SAroraEWMayrNOllinger, title = {Overcoming Intractability in Unsupervised Learning (Invited Talk)}}", author = "S Arora, EW Mayr, N Ollinger} } @misc{2015SAryalRGutierrezOsuna, title = {Data driven articulatory synthesis with deep neural networks}, author = {S Aryal, R Gutierrez-Osuna} } @misc{2015SBondugulaVManjunathaLSDavisDDoermann, title = {Shoe: Supervised Hashing with Output Embeddings}, author = {S Bondugula, V Manjunatha, LS Davis, D Doermann} } @misc{2015SDielemanKWWillettJDambre, title = {Rotation-invariant convolutional neural networks for galaxy morphology prediction}, author = {S Dieleman, KW Willett, J Dambre} } @misc{2015SEKahouXBouthillierPLamblinCGulcehre, title = {EmoNets: Multimodal deep learning approaches for emotion recognition in video}, author = {SE Kahou, X Bouthillier, P Lamblin, C Gulcehre} } @misc{2015SFenwick, title = {Equity-Minded Learning Environments: Pla as a Portal to Fostering Inclusive Excellence}, author = {S Fenwick} } @misc{2015SGMatthews, title = {Ai for Data Mining}, author = {SG Matthews} } @misc{2015SGaoLDuanITsang, title = {DEFEATnet--A Deep Conventional Image Representation for Image Classification}, author = {S Gao, L Duan, I Tsang} } @misc{2015SGuptaPArbelÃ¡ezRGirshickJMalik, title = {Inferring 3d Object Pose in Rgb-d Images}, author = {S Gupta, P ArbelÃ¡ez, R Girshick, J Malik} } @misc{2015SHuangHChenXDaiJChen, title = {Non-linear Learning for Statistical Machine Translation}, author = {S Huang, H Chen, X Dai, J Chen} } @misc{2015SHuangMElhoseinyAElgammalDYang, title = {Learning Hypergraph-regularized Attribute Predictors}, author = {S Huang, M Elhoseiny, A Elgammal, D Yang} } @misc{2015SIoffeCSzegedy, title = {Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift}, author = {S Ioffe, C Szegedy} } @misc{2015SJansen, title = {The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition}, author = {S Jansen} } @misc{2015SKeshmiriXZhengCMChewCKPang, title = {Application of Deep Neural Network in Estimation of the Weld Bead Parameters}, author = {S Keshmiri, X Zheng, CM Chew, CK Pang} } @misc{2015SKoyamadaYShikauchiKNakaeMKoyamaSIshii, title = {Deep learning of fMRI big data: a novel approach to subject-transfer decoding}, author = {S Koyamada, Y Shikauchi, K Nakae, M Koyama, S Ishii} } @misc{2015SLaflammeSRuan, title = {Where am I? Predicting Montreal Neighbourhoods from Google Street View Images}, author = {S Laflamme, S Ruan} } @misc{2015SMukherjeeSKDMandal, title = {F0 Modeling In Hmm-Based Speech Synthesis System Using Deep Belief Network}, author = {S Mukherjee, SKD Mandal} } @misc{2015SParkKBongDShinJLeeSChoiHJYoo, title = {4.6 A1. 93tops/w scalable deep learning/inference processor with tetra-parallel Mimd architecture for big-data applications}, author = {S Park, K Bong, D Shin, J Lee, S Choi, HJ Yoo} } @misc{2015SRKuppannagariVKPrasanna, title = {Efficient Generation of Energy and Performance Pareto Front for Fpga Designs}, author = {SR Kuppannagari, VK Prasanna} } @misc{2015SRYoung, title = {Scalable Hardware Efficient Deep Spatio-Temporal Inference Networks}, author = {SR Young} } @misc{2015SRazakarivonyFJurie, title = {Vehicle Detection in Aerial Imagery: A small target detection benchmark}, author = {S Razakarivony, F Jurie} } @misc{2015SRomdhani, title = {Implementation of Dnn-hmm Acoustic Models for Phoneme Recognition}, author = {S Romdhani} } @misc{2015SRongaliAPSarathChandarBRavindran, title = {From multiple views to single view: a neural network approach}, author = {S Rongali, AP Sarath Chandar, B Ravindran} } @misc{2015SVajdaYRangoniHCecotti, title = {Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition}, author = {S Vajda, Y Rangoni, H Cecotti} } @misc{2015SWuRLaganiÃ¨rePPayeur, title = {Improving Pedestrian Detection with Selective Gradient Self-Similarity Feature}, author = {S Wu, R LaganiÃ¨re, P Payeur} } @misc{2015SXueOAbdelHamidHJiangLDaiQLiu, title = {Fast adaptation of deep neural network based on discriminant codes for speech recognition}, author = {S Xue, O Abdel-Hamid, H Jiang, L Dai, Q Liu} } @misc{2015SYHuangYHuangNSuri, title = {Event Pattern Discovery on Ids Traces of Cloud Services}, author = {SY Huang, Y Huang, N Suri} } @misc{2015SYangLAnMKafaiBBhanu, title = {To Skip or not to Skip? A Dataset of Spontaneous Affective Response of Online Advertising (sara) for Audience Behavior Analysis}, author = {S Yang, L An, M Kafai, B Bhanu} } @misc{2015SYinCLiuZZhangYLinDWangJTejedorTFang, title = {Noisy Training for Deep Neural Networks in Speech Recognition}, author = {S Yin, C Liu, Z Zhang, Y Lin, D Wang, J Tejedor, T Fang} } @misc{2015SYinPOuyangLLiuYGuoSWei, title = {Fast Traffic Sign Recognition with a Rotation Invariant Binary Pattern Based Feature}, author = {S Yin, P Ouyang, L Liu, Y Guo, S Wei} } @misc{2015SZhangHJiang, title = {Hybrid Orthogonal Projection and Estimation (hope): A New Framework to Probe and Learn Neural Networks}, author = {S Zhang, H Jiang} } @misc{2015SZhangRBenensonBSchiele, title = {Filtered Channel Features for Pedestrian Detection}, author = {S Zhang, R Benenson, B Schiele} } @misc{2015SZhengSJayasumanaBRomeraParedesVVineet, title = {Conditional Random Fields as Recurrent Neural Networks}, author = {S Zheng, S Jayasumana, B Romera-Paredes, V Vineet} } @misc{2015TDKulkarniWWhitneyPKohliJBTenenbaum, title = {Deep Convolutional Inverse Graphics Network}, author = {TD Kulkarni, W Whitney, P Kohli, JB Tenenbaum} } @misc{2015TDrugmanYStylianouLChenXChenMJFGales, title = {Robust Excitation-based Features For Automatic Speech Recognition}, author = {T Drugman, Y Stylianou, L Chen, X Chen, MJF Gales} } @misc{2015TElDokor, title = {Method and Apparatus for Spawning Specialist Belief Propagation Networks For Adjusting Exposure Settings}, author = {T El Dokor} } @misc{2015TFlynnJOlsonGOrchard, title = {6 On Handling Occlusions Using Hmax}, author = {T Flynn, J Olson, G Orchard} } @misc{2015TGindeleSBrechtelRDillmann, title = {Learning Driver Behavior Models from Traffic Observations for Decision Making and Planning}, author = {T Gindele, S Brechtel, R Dillmann} } @misc{2015THiroyasuKHanawaUYamamoto, title = {Gender classification of subjects from cerebral blood flow changes using Deep Learning}, author = {T Hiroyasu, K Hanawa, U Yamamoto} } @misc{2015THuangLLanXFangPAnJMinFWang, title = {Promises and Challenges of Big Data Computing in Health Sciences}, author = {T Huang, L Lan, X Fang, P An, J Min, F Wang} } @misc{2015THuynhYHeSRÃ¼ger, title = {Learning Higher-Level Features with Convolutional Restricted Boltzmann Machines for Sentiment Analysis}, author = {T Huynh, Y He, S RÃ¼ger} } @misc{2015TKlatzerTPock, title = {Continuous Hyper-parameter Learning for Support Vector Machines}, author = {T Klatzer, T Pock} } @misc{2015TKuleszaMBurnettWKWongSStumpf, title = {Principles of Explanatory Debugging to Personalize Interactive Machine Learning}, author = {T Kulesza, M Burnett, WK Wong, S Stumpf} } @misc{2015TPfisterKSimonyanJCharlesAZisserman, title = {Deep Convolutional Neural Networks for Efficient Pose Estimation in Gesture Videos}, author = {T Pfister, K Simonyan, J Charles, A Zisserman} } @misc{2015TTranTDNguyenDPhungSVenkatesh, title = {Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)}, author = {T Tran, TD Nguyen, D Phung, S Venkatesh} } @misc{2015TWuBLiSCZhu, title = {Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation}, author = {T Wu, B Li, SC Zhu} } @misc{2015VDCalhoun, title = {A spectrum of sharing: maximization of information content for brain imaging data}, author = {VD Calhoun} } @misc{2015VKIthapuSRaviVSingh, title = {Convergence of gradient based pre-training in Denoising autoencoders}, author = {VK Ithapu, S Ravi, V Singh} } @misc{2015VMnihKKavukcuogluDSilverAARusuJVeness, title = {Human-level control through deep reinforcement learning}, author = {V Mnih, K Kavukcuoglu, D Silver, AA Rusu, J Veness} } @misc{2015VMygdalisAIosifidisATefasIPitas, title = {Video summarization based on Subclass Support Vector Data Description}, author = {V Mygdalis, A Iosifidis, A Tefas, I Pitas} } @misc{2015VOrdonezWLiuJDengYChoiACBergTLBerg, title = {Predicting Entry-Level Categories}, author = {V Ordonez, W Liu, J Deng, Y Choi, AC Berg, TL Berg} } @misc{2015VfromEmbedsGHintonLDengDYuGDahl, title = {Deep Neural Networks for Acoustic Modeling}, author = {V from Embeds, G Hinton, L Deng, D Yu, G Dahl} } @misc{2015WBÃ¶hmerJTSpringenbergJBoedecker, title = {Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning â€¦}, author = {W BÃ¶hmer, JT Springenberg, J Boedecker} } @misc{2015WGongYHuangJGonzalez, title = {An Effective Solution to Double Counting Problem in Human Pose Estimation}, author = {W Gong, Y Huang, J Gonzalez} } @misc{2015WHuYHuangWLiFZhangHLi, title = {Deep Convolutional Neural Networks for Hyperspectral Image Classification}, author = {W Hu, Y Huang, W Li, F Zhang, H Li} } @misc{2015WKeYZhangPWeiQYeJJiao, title = {Pedestrian Detection Via Pca Filters Based Convolutional Channel}, author = {W Ke, Y Zhang, P Wei, Q Ye, J Jiao} } @misc{2015WMCzarneckiJTabor, title = {Multithreshold Entropy Linear Classifier: Theory and Applications}, author = {WM Czarnecki, J Tabor} } @misc{2015WShaoXTianPWang, title = {Soft sensor development for nonlinear and timeâ€varying processes based on supervised ensemble learning with improved process state partition}, author = {W Shao, X Tian, P Wang} } @misc{2015WShenXWangYWangXBaiZZhang, title = {DeepContour: A Deep Convolutional Feature Learned by Positive-sharing Loss for Contour Detection draft version, Cvpr2015}, author = {W Shen, X Wang, Y Wang, X Bai, Z Zhang} } @misc{2015WTayNNuoJBotzheimCKLooNKubota, title = {Robust face recognition via transfer learning for robot partner}, author = {W Tay, N Nuo, J Botzheim, CK Loo, N Kubota} } @misc{2015WWangGChenTTADinhJGaoBCOoiKLTan, title = {Singa: A Distributed System for Deep Learning}, author = {W Wang, G Chen, TTA Dinh, J Gao, BC Ooi, KL Tan} } @misc{2015WWangJYangJXiaoSLiDZhou, title = {Face Recognition Based on Deep Learning}, author = {W Wang, J Yang, J Xiao, S Li, D Zhou} } @misc{2015WYWangMWen, title = {I Can Has Cheezburger? A Nonparanormal Approach to Combining Textual and Visual Information for Predicting and Generating Popular Meme Descriptions}, author = {WY Wang, M Wen} } @misc{2015WZShaoMElad, title = {Simple, Accurate, and Robust Nonparametric Blind Super-Resolution}, author = {WZ Shao, M Elad} } @misc{2015WZhuJMiaoLQing, title = {Constrained Extreme Learning Machines: A Study on Classification Cases}, author = {W Zhu, J Miao, L Qing} } @misc{2015XChenSXiangCLLiuCHPan, title = {Aircraft Detection by Deep Convolutional Neural Networks}, author = {X Chen, S Xiang, CL Liu, CH Pan} } @misc{2015XGaoYJiangTChenDHuang, title = {Optimizing Scheduling of Refinery Operations based on Piecewise Linear Models}, author = {X Gao, Y Jiang, T Chen, D Huang} } @misc{2015XLiFZhaoYGuo, title = {Conditional Restricted Boltzmann Machines for Multi-label Learning with Incomplete Labels}, author = {X Li, F Zhao, Y Guo} } @misc{2015XLiangSLiuXShenJYangLLiuLLinSYan, title = {Deep Human Parsing with Active Template Regression}, author = {X Liang, S Liu, X Shen, J Yang, L Liu, L Lin, S Yan} } @misc{2015XMaHYuYWangYWang, title = {Large-Scale Transportation Network Congestion Evolution Prediction Using Deep Learning Theory}, author = {X Ma, H Yu, Y Wang, Y Wang} } @misc{2015XNiuYZhuQCaoXZhangWXieKZheng, title = {An Online-Traffic-Prediction Based Route Finding Mechanism for Smart City}, author = {X Niu, Y Zhu, Q Cao, X Zhang, W Xie, K Zheng} } @misc{2015XNiuYZhuXZhang, title = {DeepSense: A novel learning mechanism for traffic prediction with taxi Gps traces}, author = {X Niu, Y Zhu, X Zhang} } @misc{2015XQiCGLiGZhaoXHongMPietikÃ¤inen, title = {Dynamic texture and scene classification by transferring deep image features}, author = {X Qi, CG Li, G Zhao, X Hong, M PietikÃ¤inen} } @misc{2015XShulanWJilin, title = {The Research on Cross-Language Emotion Recognition Algorithm for Hearing Aid}, author = {X Shulan, W Jilin} } @misc{2015XSongZLiuXYangJYangYQi, title = {Extended Semi-supervised Fuzzy Learning Method for Nonlinear Outliers via Pattern Discovery}, author = {X Song, Z Liu, X Yang, J Yang, Y Qi} } @misc{2015XWangRGuoCKambhamettu, title = {Deeply-Learned Feature for Age Estimation}, author = {X Wang, R Guo, C Kambhamettu} } @misc{2015XZhangFXYuSFChangSWang, title = {Deep Transfer Network: Unsupervised Domain Adaptation}, author = {X Zhang, FX Yu, SF Chang, S Wang} } @misc{2015XZhangYFuAZangLSigalGAgam, title = {Learning Classifiers from Synthetic Data Using a Multichannel Autoencoder}, author = {X Zhang, Y Fu, A Zang, L Sigal, G Agam} } @misc{2015XZhaoXShiSZhang, title = {Facial Expression Recognition via Deep Learning}, author = {X Zhao, X Shi, S Zhang} } @misc{2015XZhengZZengZChenYYuCRong, title = {Detecting spammers on social Networks}, author = {X Zheng, Z Zeng, Z Chen, Y Yu, C Rong} } @misc{2015YBengioDHLeeJBornscheinZLin, title = {Towards Biologically Plausible Deep Learning}, author = {Y Bengio, DH Lee, J Bornschein, Z Lin} } @misc{2015YChenXZhaoXJia, title = {Spectralâ€“Spatial Classification of Hyperspectral Data Based on Deep Belief Network}, author = {Y Chen, X Zhao, X Jia} } @misc{2015YChengFXYuRSFerisSKumarAChoudhary, title = {Fast Neural Networks with Circulant Projections}, author = {Y Cheng, FX Yu, RS Feris, S Kumar, A Choudhary} } @misc{2015YDengYZhong, title = {Keystroke Dynamics Advances for Mobile Devices Using Deep Neural Network}, author = {Y Deng, Y Zhong} } @misc{2015YDengYZhongKeystrokeDynamicsUser, title = {Keystroke Dynamics User Authentication Using Advanced Machine Learning Methods}, author = {Y Deng, Y Zhong} } @misc{2015YFuTMHospedalesTXiangSGong, title = {Transductive Multi-view Zero-Shot Learning}, author = {Y Fu, TM Hospedales, T Xiang, S Gong} } @misc{2015YGJiangZWuJWangXXueSFChang, title = {Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks}, author = {YG Jiang, Z Wu, J Wang, X Xue, SF Chang} } @misc{2015YHChenSUParkDWeiGNewstadtMJackson, title = {A Dictionary Approach to Ebsd Indexing}, author = {YH Chen, SU Park, D Wei, G Newstadt, M Jackson} } @misc{2015YHouCWangYJi, title = {The Research of Event Detection and Characterization Technology of Ticket Gate in the Urban Rapid Rail Transit}, author = {Y Hou, C Wang, Y Ji} } @misc{2015YHuangRWuYSunWWangXDing, title = {Vehicle Logo Recognition System Based on Convolutional Neural Networks With a Pretraining Strategy}, author = {Y Huang, R Wu, Y Sun, W Wang, X Ding} } @misc{2015YHuangXShiJSuYChenGHuang, title = {Unsupervised word sense induction using rival penalized competitive learning}, author = {Y Huang, X Shi, J Su, Y Chen, G Huang} } @misc{2015YLWang, title = {Interactions Between Gaussian Processes and Bayesian Estimation}, author = {YL Wang} } @misc{2015YLiCYChenWWWasserman, title = {Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters}, author = {Y Li, CY Chen, WW Wasserman} } @misc{2015YLiFSohelMBennamounHLei, title = {Heterogeneous Multi-column ConvNets with a Fusion Framework for Object Recognition}, author = {Y Li, F Sohel, M Bennamoun, H Lei} } @misc{2015YLiuXFengZZhou, title = {Multimodal Video Classification with Stacked Contractive Autoencoders}, author = {Y Liu, X Feng, Z Zhou} } @misc{2015YMrouehEMarcheretVGoel, title = {Deep Multimodal Learning for Audio-Visual Speech Recognition}, author = {Y Mroueh, E Marcheret, V Goel} } @misc{2015YNDauphinHdeVriesJChungYBengio, title = {RMSProp and equilibrated adaptive learning rates for non-convex optimization}, author = {YN Dauphin, H de Vries, J Chung, Y Bengio} } @misc{2015YPerwej, title = {An Evaluation of Deep Learning Miniature Concerning in Soft Computing}, author = {Y Perwej} } @misc{2015YSManjiliMNiknamfar, title = {Big Data Analytic: Cases for Communications Systems Modeling and Renewable Energy Forecast}, author = {YS Manjili, M Niknamfar} } @misc{2015YShu, title = {Deep Convolutional Neural Networks for Object Extraction from High Spatial Resolution Remotely Sensed Imagery}, author = {Y Shu} } @misc{2015YSunBHuJDengXLi, title = {Supervised descent method with low rank and sparsity constraints for robust face alignment}, author = {Y Sun, B Hu, J Deng, X Li} } @misc{2015YSunDLiangXWangXTang, title = {DeepID3: Face Recognition with Very Deep Neural Networks}, author = {Y Sun, D Liang, X Wang, X Tang} } @misc{2015YWangYLiMXiongLJin, title = {Random Bits Regression: a Strong General Predictor for Big Data}, author = {Y Wang, Y Li, M Xiong, L Jin} } @misc{2015YXiaLZhangWXuZShanYLiu, title = {Recognizing Multi-view Objects with Occlusions using a Deep Architecture}, author = {Y Xia, L Zhang, W Xu, Z Shan, Y Liu} } @misc{2015YYanXCYinSLiMYangHWHao, title = {Learning Document Semantic Representation with Hybrid Deep Belief Network}, author = {Y Yan, XC Yin, S Li, M Yang, HW Hao} } @misc{2015YYangTMHospedales, title = {Deep Neural Networks for Sketch Recognition}, author = {Y Yang, TM Hospedales} } @misc{2015YYuanLMouXLu, title = {Scene Recognition by Manifold Regularized Deep Learning Architecture}, author = {Y Yuan, L Mou, X Lu} } @misc{2015YZHUCYAOXBAI, title = {Scene Text Detection and Recognition: Recent Advances and Future Trends}, author = {Y ZHU, C YAO, X BAI} } @misc{2015YZhangZDuan, title = {Sound Retrieval From Vocal Imitation Queries Based On Deep Neural Networks}, author = {Y Zhang, Z Duan} } @misc{2015YZhaoZGaoLWangLZhou, title = {Experimental Study of Unsupervised Feature Learning for HEp-2 Cell Images Clustering}, author = {Y Zhao, Z Gao, L Wang, L Zhou} } @misc{2015YZhuRUrtasunRSalakhutdinovSFidler, title = {segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection}, author = {Y Zhu, R Urtasun, R Salakhutdinov, S Fidler} } @misc{2015ZCaoFWeiLDongSLiMZhou, title = {Ranking with Recursive Neural Networks and Its Application to Multi-document Summarization}, author = {Z Cao, F Wei, L Dong, S Li, M Zhou} } @misc{2015ZChenLMaLXuCTanYYan, title = {Imaging and representation learning of solar radio spectrums for classification}, author = {Z Chen, L Ma, L Xu, C Tan, Y Yan} } @misc{2015ZChengDSoudryZMaoZLan, title = {Study on Binary Multilayer Neural Networks with Ebp Algorithm on Image Classification}, author = {Z Cheng, D Soudry, Z Mao, Z Lan} } @misc{2015ZCuiSSGeZCaoJYangHRen, title = {Analysis of Different Sparsity Methods in Constrained Rbm for Sparse Representation in Cognitive Robotic Perception}, author = {Z Cui, SS Ge, Z Cao, J Yang, H Ren} } @misc{2015ZCuiZCaoJYangHRen, title = {Hierarchical Recognition System for Target Recognition from Sparse Representations}, author = {Z Cui, Z Cao, J Yang, H Ren} } @misc{2015ZFengLJinDTaoSHuang, title = {DLANet: A Manifold-Learning-based Discriminative Feature Learning Network for Scene Classification}, author = {Z Feng, L Jin, D Tao, S Huang} } @misc{2015ZGanRHenaoDCarlsonLCarin, title = {Learning Deep Sigmoid Belief Networks with Data Augmentation}, author = {Z Gan, R Henao, D Carlson, L Carin} } @misc{2015ZHUANGWXUEQMAO, title = {Speech emotion recognition with unsupervised feature learning}, author = {Z HUANG, W XUE, Q MAO} } @misc{2015ZJunlinCHengHTongwenXHuiping, title = {A Distributional Representation Model For Collaborative Filtering}, author = {Z Junlin, C Heng, H Tongwen, X Huiping} } @misc{2015ZMingABugeauJLRouasTShochi, title = {Facial Action Units Intensity Estimation by the Fusion of Features with Multi-kernel Support Vector Machine}, author = {Z Ming, A Bugeau, JL Rouas, T Shochi} } @misc{2015ZSunYFanBPFLelieveldtMvandeGiessen, title = {Detection of Alzheimer's disease using group lasso SVM-based region selection}, author = {Z Sun, Y Fan, BPF Lelieveldt, M van de Giessen} } @misc{2015ZZuoGWangBShuaiLZhaoQYang, title = {Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification}, author = {Z Zuo, G Wang, B Shuai, L Zhao, Q Yang} } @misc{2015Ä°AtÄ±lSKalkan, title = {Towards an Embodied Developing Vision System}, author = {Ä° AtÄ±l, S Kalkan} } @incollection{Lee+etal08:sparseDBN, title = {Sparse Deep Belief Net Model for Visual Area {V2}}, author = {Honglak Lee and Chaitanya Ekanadham and Andrew~Y. Ng}, booktitle = {Advances in Neural Information Processing Systems 20}, pages = {873--880}, year = {2008} } @inproceedings{Lee+etal09:convDBN, title = {Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations}, author = {Lee, Honglak and Grosse, Roger and Ranganath, Rajesh and Ng, Andrew Y.}, booktitle = {Proceedings of the 26th International Conference on Machine Learning}, pages = {609--616}, year = {2009} } @incollection{Lee+etal09:convDBNAudio, title = {Unsupervised Feature Learning for Audio Classification using Convolutional Deep Belief Networks}, author = {Honglak Lee and Yan Largman and Peter Pham and Andrew~Y. Ng}, booktitle = {Advances in Neural Information Processing Systems 22}, pages = {1096--1104} } @incollection{NIPS2012_4824, title = {ImageNet Classification with Deep Convolutional Neural Networks}, author = {Alex Krizhevsky and Sutskever, Ilya and Geoffrey E. Hinton}, booktitle = {Advances in Neural Information Processing Systems 25}, pages = {1097--1105}, year = {2012}, publisher = {Curran Associates, Inc.} } @inproceedings{Sohn+etal:iccv2011, title = {Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition}, author = {Sohn, Kihyuk and Jung, Dae Yon and Lee, Honglak and Hero III, Alfred}, booktitle = {Proceedings of 13th International Conference on Computer Vision}, year = {2011} } @article{albornozspoken, title = {Spoken emotion recognition using deep learning}, author = {Albornoz, EM and S{\'a}nchez-Guti{\'e}rrez, M and Martinez-Licona, F and Rufiner, HL and Goddard, J} } @article{alexandre3d, title = {3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels}, author = {Alexandre, Lu{\'\i}s A} } @article{amaral2014transfer, title = {Transfer of Learning Across Deep Networks to Improve Performance in Problems with Few Labelled Data}, author = {Amaral, Telmo}, year = {2014} } @article{anderson2014quantifying, title = {Quantifying the Energy Efficiency of Object Recognition and Optical Flow}, author = {Anderson, Michael and Iandola, Forrest and Keutzer, Kurt}, year = {2014} } @article{anderson2014uav, title = {UAV Application for DARPA PERFECT}, author = {Anderson, Michael and Iandola, Forrest and Keutzer, Kurt}, year = {2014} } @article{aslamlearning, title = {Learning Distributed Representations of Natural Language Text with Artificial Neural Networks}, author = {Aslam, Ali} } @article{baccouchedeep, title = {Deep learning of split temporal context for automatic speech recognition}, author = {Baccouche, Moez and Besset, Beno{\^\i}t and Collen, Patrice and Le Blouch, Olivier} } @article{bahdanau2014neural, title = {Neural Machine Translation by Jointly Learning to Align and Translate}, author = {Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1409.0473}, year = {2014} } @article{baldi2014deep, title = {Deep Learning in High-Energy Physics: Improving the Search for Exotic Particles}, author = {Baldi, Pierre and Sadowski, Peter and Whiteson, Daniel}, journal = {arXiv preprint arXiv:1402.4735}, year = {2014} } @article{baldi2014searching, title = {Searching for exotic particles in high-energy physics with deep learning}, author = {Baldi, P and Sadowski, P and Whiteson, D}, journal = {Nature communications}, volume = {5}, year = {2014}, publisher = {Nature Publishing Group} } @article{baucom2014survey, title = {Survey and Implementation of Computer Vision Techniques for Humanoid Robots}, author = {Baucom, Aaron}, year = {2014} } @article{bengio2014towards, title = {Towards Real-Time Image Understanding with Convolutional Networks}, author = {Bengio, Yoshua}, year = {2014} } @inproceedings{besaw2014deep, title = {Deep learning algorithms for detecting explosive hazards in ground penetrating radar data}, author = {Besaw, Lance E and Stimac, Philip J}, booktitle = {SPIE Defense+ Security}, pages = {90720Y--90720Y}, year = {2014}, organization = {International Society for Optics and Photonics} } @phdthesis{bhutani2014alternate, title = {Alternate Layer Sparsity and Intermediate Fine-tuning for Deep Autoencoders}, author = {Bhutani, Ankit}, year = {2014}, school = {INDIAN INSTITUTE OF TECHNOLOGY, KANPUR} } @inproceedings{bian2014reducing, title = {Reducing structure of deep Convolutional Neural Networks for Huawei Accurate and Fast Mobile Video Annotation Challenge}, author = {Bian, Yunlong and Dong, Yuan and Bai, Hongliang and Liu, Bo and Wang, Kai and Liu, Yinan}, booktitle = {Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on}, pages = {1--6}, year = {2014}, organization = {IEEE} } @article{biem2014neural, title = {Neural Networks: A Review}, author = {Biem, Alain}, journal = {Data Classification: Algorithms and Applications}, pages = {205}, year = {2014}, publisher = {CRC Press} } @article{bordes2014semantic, title = {A semantic matching energy function for learning with multi-relational data}, author = {Bordes, Antoine and Glorot, Xavier and Weston, Jason and Bengio, Yoshua}, journal = {Machine Learning}, volume = {94}, number = {2}, pages = {233--259}, year = {2014}, publisher = {Springer} } @article{bornschein2014reweighted, title = {Reweighted Wake-Sleep}, author = {Bornschein, J{\"o}rg and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1406.2751}, year = {2014} } @article{bottou2014machine, title = {From machine learning to machine reasoning}, author = {Bottou, L{\'e}on}, journal = {Machine Learning}, volume = {94}, number = {2}, pages = {133--149}, year = {2014}, publisher = {Springer} } @article{bruckner2014ml, title = {ML-o-scope: a diagnostic visualization system for deep machine learning pipelines}, author = {Bruckner, Daniel}, year = {2014} } @article{bumulti, title = {Multi-modal Feature Fusion for 3D Shape Recognition and Retrieval}, author = {Bu, Shuhui and Cheng, Shaoguang and Liu, Zhenbao and Han, Junwei}, publisher = {IEEE} } @article{campbell2014using, title = {Using Deep Belief Networks for Vector-Based Speaker Recognition}, author = {Campbell, WM}, year = {2014} } @article{canny2014interactive, title = {Interactive Machine Learning}, author = {Canny, John}, journal = {University of California, Berkeley}, year = {2014} } @article{chan2014distributed, title = {Distributed Asynchronous Optimization of Convolutional Neural Networks}, author = {Chan, William and Lane, Ian and Gradients, Sparse and Momentum, Master and Decay, Gradient}, year = {2014} } @article{chatfield2014return, title = {Return of the Devil in the Details: Delving Deep into Convolutional Nets}, author = {Chatfield, Ken and Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew}, journal = {arXiv preprint arXiv:1405.3531}, year = {2014} } @inproceedings{chen2014fast, title = {A fast deep learning system using GPU}, author = {Chen, Zhilu and Wang, Jing and He, Haibo and Huang, Xinming}, booktitle = {Circuits and Systems (ISCAS), 2014 IEEE International Symposium on}, pages = {1552--1555}, year = {2014}, organization = {IEEE} } @article{chenbig, title = {Big Data Deep Learning: Challenges and Perspectives}, author = {Chen, Xue-wen and Lin, Xiaotong}, publisher = {IEEE} } @article{cheng2014language, title = {Language Modeling with Sum-Product Networks}, author = {Cheng, Wei-Chen and Kok, Stanley and Pham, Hoai Vu and Chieu, Hai Leong and Chai, Kian Ming A}, year = {2014} } @article{chenvoice, title = {Voice Conversion Using Deep Neural Networks with Layer-Wise Generative Training}, author = {Chen, Ling-Hui and Ling, Zhen-Hua and Liu, Li-Juan and Dai, Li-Rong}, publisher = {IEEE} } @article{chernodub2014training, title = {Training Neural Networks for classification using the Extended Kalman Filter: A comparative study}, author = {Chernodub, AN}, journal = {Optical Memory and Neural Networks}, volume = {23}, number = {2}, pages = {96--103}, year = {2014}, publisher = {Springer} } @article{cho2014exponentially, title = {Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning}, author = {Cho, Kyunghyun and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1406.7362}, year = {2014} } @article{cho2014learning, title = {Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation}, author = {Cho, Kyunghyun and van Merrienboer, Bart and Gulcehre, Caglar and Bougares, Fethi and Schwenk, Holger and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1406.1078}, year = {2014} } @incollection{chu2014analysis, title = {Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks}, author = {Chu, Joseph Lin and Krzy{\.z}ak, Adam}, booktitle = {Advances in Artificial Intelligence}, pages = {59--70}, year = {2014}, publisher = {Springer} } @phdthesis{chu2014using, title = {Using Support Vector Machines, Convolutional Neural Networks and Deep Belief Networks for Partially Occluded Object Recognition}, author = {Chu, Joseph Lin}, year = {2014}, school = {Concordia University} } @article{cliftonartificial, title = {Artificial Neural Networks}, author = {Clifton, David A} } @inproceedings{conti2014brain, title = {Brain-inspired Classroom Occupancy Monitoring on a Low-Power Mobile Platform}, author = {Conti, Francesco and Pullini, Antonio and Benini, Luca}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, pages = {610--615}, year = {2014} } @incollection{cui2014deep, title = {Deep Network Cascade for Image Super-resolution}, author = {Cui, Zhen and Chang, Hong and Shan, Shiguang and Zhong, Bineng and Chen, Xilin}, booktitle = {Computer Vision--ECCV 2014}, pages = {49--64}, year = {2014}, publisher = {Springer} } @inproceedings{cvpr2012deepverification, title = {Learning hierarchical representations for face verification with convolutional deep belief networks}, author = {Huang, G.~B. and Lee, H. and Learned-Miller, E.}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition}, pages = {2518--2525}, year = {2012} } @inproceedings{cvpr2013aug, title = {Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling}, author = {Kae, Andrew and Sohn, Kihyuk and Lee, Honglak and Learned-Miller, Erik}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition}, pages = {2019--2026}, year = {2013} } @inproceedings{cvpr2013bbprbm, title = {Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines}, author = {Mittelman, Roni and Lee, Honglak and Kuipers, Benjamin and Savarese, Silvio}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition}, pages = {476--483}, year = {2013} } @article{dahl2014multi, title = {Multi-task Neural Networks for QSAR Predictions}, author = {Dahl, George E and Jaitly, Navdeep and Salakhutdinov, Ruslan}, journal = {arXiv preprint arXiv:1406.1231}, year = {2014} } @article{dasigimodeling, title = {Modeling Newswire Events using Neural Networks for Anomaly Detection}, author = {Dasigi, Pradeep and Hovy, Eduard} } @article{dauphin2014identifying, title = {Identifying and attacking the saddle point problem in high-dimensional non-convex optimization}, author = {Dauphin, Yann and Pascanu, Razvan and Gulcehre, Caglar and Cho, Kyunghyun and Ganguli, Surya and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1406.2572}, year = {2014} } @article{debest, title = {Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images}, author = {de Andrade, Anderson} } @article{dedeep, title = {Deep learning: Modeling high-level face features through deep networks}, author = {de Souza J{\'u}nior, Nelson Forte} } @article{deng2014tutorial, title = {A tutorial survey of architectures, algorithms, and applications for deep learning}, author = {Deng, Li}, journal = {APSIPA Transactions on Signal and Information Processing}, volume = {3}, pages = {e2}, year = {2014}, publisher = {Cambridge Univ Press} } @article{dengdeep, title = {DEEP LEARNING}, author = {Deng, Li and Yu, Dong} } @article{denton2014exploiting, title = {Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation}, author = {Denton, Emily and Zaremba, Wojciech and Bruna, Joan and LeCun, Yann and Fergus, Rob}, journal = {arXiv preprint arXiv:1404.0736}, year = {2014} } @article{derfeature, title = {Feature Selection and Learning for Semantic Segmentation}, author = {DER TECHNISCHEN, UNIVERSIT AT MUNCHEN} } @article{ding2014mental, title = {Mental Rotation by Optimizing Transforming Distance}, author = {Ding, Weiguang and Taylor, Graham W}, journal = {arXiv preprint arXiv:1406.3010}, year = {2014} } @inproceedings{dong2014adaptive, title = {Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis}, author = {Dong, Li and Wei, Furu and Zhou, Ming and Xu, Ke}, booktitle = {Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI)}, year = {2014} } @inproceedings{dong2014adarnn, title = {Adaptive recursive neural network for target-dependent twitter sentiment classification}, author = {Dong, Li and Wei, Furu and Tan, Chuanqi and Tang, Duyu and Zhou, Ming and Xu, Ke}, booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)}, pages = {49--54}, year = {2014} } @incollection{dong2014learning, title = {Learning a deep convolutional network for image super-resolution}, author = {Dong, Chao and Loy, Chen Change and He, Kaiming and Tang, Xiaoou}, booktitle = {Computer Vision--ECCV 2014}, pages = {184--199}, year = {2014}, publisher = {Springer} } @article{dong2014rankcnn, title = {RankCNN: When learning to rank encounters the pseudo preference feedback}, author = {Dong, Yuan and Huang, Chong and Liu, Wei}, journal = {Computer Standards \& Interfaces}, volume = {36}, number = {3}, pages = {554--562}, year = {2014}, publisher = {Elsevier} } @inproceedings{dos2014deep, title = {Deep convolutional neural networks for sentiment analysis of short texts}, author = {dos Santos, C{\i}cero Nogueira and Gatti, Ma{\i}ra}, booktitle = {Proceedings of the 25th International Conference on Computational Linguistics (COLING), Dublin, Ireland}, year = {2014} } @article{dos2014think, title = {Think Positive: Towards Twitter Sentiment Analysis from Scratch}, author = {dos Santos, C{\i}cero Nogueira}, journal = {SemEval 2014}, pages = {647}, year = {2014} } @incollection{evans2014machines, title = {Machines Learning-Towards a New Synthetic Autobiographical Memory}, author = {Evans, Mathew H and Fox, Charles W and Prescott, Tony J}, booktitle = {Biomimetic and Biohybrid Systems}, pages = {84--96}, year = {2014}, publisher = {Springer} } @article{foxtowards, title = {Towards an Understanding of Facets and Exemplars of Big Data Applications}, author = {Fox, Geoffrey C and Jha, Shantenu and Qiu, Judy and Luckow, Andre} } @article{fuentes2014detection, title = {Detection of retransmissions in 10G Ethernet using GPUs}, author = {Fuentes, Paula Roquero}, year = {2014}, publisher = {hgpu. org} } @article{gangireddy2014feed, title = {Feed Forward Pre-training for Recurrent Neural Network Language Models}, author = {Gangireddy, Siva Reddy and McInnes, Fergus and Renals, Steve}, year = {2014} } @article{ganin2014n, title = {$ N\^{} 4$-Fields: Neural Network Nearest Neighbor Fields for Image Transforms}, author = {Ganin, Yaroslav and Lempitsky, Victor}, journal = {arXiv preprint arXiv:1406.6558}, year = {2014} } @inproceedings{gao2014modeling, title = {Modeling interestingness with deep neural networks}, author = {Gao, Jianfeng and Pantel, Patrick and Gamon, Michael and He, Xiaodong and Deng, Li and Shen, Yelong}, booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing}, year = {2014} } @article{geras2014scheduled, title = {Scheduled denoising autoencoders}, author = {Geras, Krzysztof J and Sutton, Charles}, journal = {arXiv preprint arXiv:1406.3269}, year = {2014} } @inproceedings{gokhale2014240, title = {A 240 G-ops/s Mobile Coprocessor for Deep Neural Networks}, author = {Gokhale, Vinayak and Jin, Jonghoon and Dundar, Aysegul and Martini, Berin and Culurciello, Eugenio}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, pages = {682--687}, year = {2014} } @article{goodfellow2014generative, title = {Generative Adversarial Networks}, author = {Goodfellow, Ian J and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1406.2661}, year = {2014} } @phdthesis{gravelines2014deep, title = {DEEP LEARNING VIA STACKED SPARSE AUTOENCODERS FOR AUTOMATED VOXEL-WISE BRAIN PARCELLATION BASED ON FUNCTIONAL CONNECTIVITY (Thesis format: Monograph)}, author = {Gravelines, C{\'e}line}, year = {2014}, school = {The University of Western Ontario} } @inproceedings{gu2014implementation, title = {Implementation and evaluation of deep neural networks (DNN) on mainstream heterogeneous systems}, author = {Gu, Junli and Zhu, Maohua and Zhou, Zhitao and Zhang, Feng and Lin, Zhen and Zhang, Qianfeng and Breternitz, Mauricio}, booktitle = {Proceedings of 5th Asia-Pacific Workshop on Systems}, pages = {12}, year = {2014}, organization = {ACM} } @incollection{gulcehre2014learned, title = {Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks}, author = {Gulcehre, Caglar and Cho, Kyunghyun and Pascanu, Razvan and Bengio, Yoshua}, booktitle = {Machine Learning and Knowledge Discovery in Databases}, pages = {530--546}, year = {2014}, publisher = {Springer} } @article{gunawan2014deep, title = {DEEP EXTREME TRACKER BASED ON BOOTSTRAP PARTICLE FILTER}, author = {GUNAWAN, ALEXANDER AS and FANANY, MOHAMAD IVAN and JATMIKO, WISNU}, journal = {Journal of Theoretical and Applied Information Technology}, volume = {66}, number = {3}, year = {2014} } @incollection{gupta2014learning, title = {Learning Rich Features from RGB-D Images for Object Detection and Segmentation}, author = {Gupta, Saurabh and Girshick, Ross and Arbel{\'a}ez, Pablo and Malik, Jitendra}, booktitle = {Computer Vision--ECCV 2014}, pages = {345--360}, year = {2014}, publisher = {Springer} } @article{gupta2014query, title = {Query Expansion for Multi-script Information Retrieval}, author = {Gupta, Parth and Bali, Kalika and Banchs, Rafael E and Choudhury, Monojit and Rosso, Paolo}, year = {2014} } @phdthesis{han2014feature, title = {FEATURE GENERATION FOR QUANTIFICATION OF VISUAL SIMILARITY}, author = {Han, Tianning Steven}, year = {2014}, school = {Rensselaer Polytechnic Institute} } @article{han2014object, title = {Object recognition with hierarchical discriminant saliency networks}, author = {Han, Sunhyoung and Vasconcelos, Nuno}, journal = {Frontiers in Computational Neuroscience}, volume = {8}, pages = {109}, year = {2014}, publisher = {Frontiers} } @article{hannagan2014deep, title = {Deep Learning of Orthographic Representations in Baboons}, author = {Hannagan, Thomas and Ziegler, Johannes C and Dufau, St{\'e}phane and Fagot, Jo{\"e}l and Grainger, Jonathan}, journal = {PloS one}, volume = {9}, number = {1}, pages = {e84843}, year = {2014}, publisher = {Public Library of Science} } @phdthesis{hartmann2014friedrich, title = {Discriminative Convolutional Sum-Product Networks on GPU}, author = {Hartmann, Tobias}, year = {2014}, school = {Rheinische Friedrich-Wilhelms-Universit{"a}t Bonn} } @article{he2014deep, title = {Deep Learning}, author = {He, Xiaodong and Gao, Jianfeng and Deng, Li}, year = {2014} } @inproceedings{heigold2014asynchronous, title = {Asynchronous stochastic optimization for sequence training of deep neural networks}, author = {Heigold, Georg and McDermott, Erik and Vanhoucke, Vincent and Senior, Andrew and Bacchiani, Michiel}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {5587--5591}, year = {2014}, organization = {IEEE} } @article{hjelm2014restricted, title = {Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks}, author = {Hjelm, R Devon and Calhoun, Vince D and Salakhutdinov, Ruslan and Allen, Elena A and Adali, Tulay and Plis, Sergey M}, journal = {NeuroImage}, volume = {96}, pages = {245--260}, year = {2014}, publisher = {Elsevier} } @article{hoftfast, title = {Fast Semantic Segmentation of RGB-D Scenes with GPU-Accelerated Deep Neural Networks}, author = {H{\"o}ft, Nico and Schulz, Hannes and Behnke, Sven} } @inproceedings{hua2014mining, title = {Mining knowledge from clicks: MSR-Bing image retrieval challenge}, author = {Hua, Xian-Sheng and Ye, Ming and Li, Jin}, booktitle = {Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on}, pages = {1--4}, year = {2014}, organization = {IEEE} } @inproceedings{huang2014deep, title = {Deep process neural network for temporal deep learning}, author = {Huang, Wenhao and Hong, Haikun and Song, Guojie and Xie, Kunqing}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {465--472}, year = {2014}, organization = {IEEE} } @article{huang2014historical, title = {A historical perspective of speech recognition}, author = {Huang, Xuedong and Baker, James and Reddy, Raj}, journal = {Communications of the ACM}, volume = {57}, number = {1}, pages = {94--103}, year = {2014}, publisher = {ACM} } @inproceedings{huang2014kernel, title = {Kernel methods match deep neural networks on timit}, author = {Huang, Po-Sen and Avron, Haim and Sainath, Tara N and Sindhwani, Vikas and Ramabhadran, Bhuvana}, booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing}, volume = {1}, pages = {6}, year = {2014} } @article{huangdeep, title = {Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning}, author = {Huang, Wenhao and Song, Guojie and Hong, Haikun and Xie, Kunqing}, publisher = {IEEE} } @article{iandola2014densenet, title = {DenseNet: Implementing Efficient ConvNet Descriptor Pyramids}, author = {Iandola, Forrest and Moskewicz, Matt and Karayev, Sergey and Girshick, Ross and Darrell, Trevor and Keutzer, Kurt}, journal = {arXiv preprint arXiv:1404.1869}, year = {2014} } @inproceedings{icml2013pgbm, title = {Learning and Selecting Features Jointly with Point-wise Gated {Boltzmann} Machines}, author = {Sohn, Kihyuk and Zhou, Guanyu and Lee, Chansoo and Lee, Honglak}, booktitle = {Proceedings of The 30th International Conference on Machine Learning}, pages = {217--225}, year = {2013} } @inproceedings{icml2014srtrbm, title = {Structured Recurrent Temporal Restricted Boltzmann Machines}, author = {Roni Mittelman and Benjamin Kuipers and Silvio Savarese and Honglak Lee}, booktitle = {Proceedings of The 31st International Conference on Machine Learning}, year = {2014} } @article{jaderberg2014speeding, title = {Speeding up Convolutional Neural Networks with Low Rank Expansions}, author = {Jaderberg, Max and Vedaldi, Andrea and Zisserman, Andrew}, journal = {arXiv preprint arXiv:1405.3866}, year = {2014} } @article{jaderberg2014synthetic, title = {Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition}, author = {Jaderberg, Max and Simonyan, Karen and Vedaldi, Andrea and Zisserman, Andrew}, journal = {arXiv preprint arXiv:1406.2227}, year = {2014} } @article{jia2014caffe, title = {Caffe: Convolutional Architecture for Fast Feature Embedding}, author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor}, journal = {arXiv preprint arXiv:1408.5093}, year = {2014} } @article{jintraining, title = {Training Large Scale Deep Neural Networks on the Intel Xeon Phi Many-core Coprocessor}, author = {Jin, Lei and Wang, Zhaokang and Gu, Rong and Yuan, Chunfeng and Huang, Yihua} } @misc{jones2014learning, title = {THE LEARNING MACHINES}, author = {Jones, Nicola}, year = {2014}, publisher = {Nature Publishing Group MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND} } @article{kandaswamy2014improve, title = {Improve Performance in Deep Neural Networks:(1) Cost Functions, and (2) Reusable learning}, author = {Kandaswamy, Chetak}, year = {2014} } @inproceedings{kandaswamy2014improving, title = {Improving Deep Neural Network Performance by Reusing Features Trained with Transductive Transference}, author = {Kandaswamy, Chetak and Silva, Lu{\i}s and Alexandre, Lu{\i}s and Sa, J Marques and Santos, JM}, booktitle = {Proceedings of the 24th International Conference on Artificial Neural Networks}, year = {2014} } @article{kandaswamyimproving, title = {Improving Accuracy on Transductive Transfer Learning by Reusing SDA}, author = {Kandaswamy, Chetak and de S{\'a}, Joaquim Marques and Silva, Lu{\'\i}s M and Alexandre, Lu{\'\i}s A and Santos, Jorge M} } @article{kang2014statistical, title = {Statistical Parametric Speech Synthesis using Weighted Multi-distribution Deep Belief Network}, author = {Kang, Shiyin and Meng, Helen}, year = {2014} } @article{kangdeep, title = {A DEEP LEARNING APPROACH TO DOCUMENT IMAGE QUALITY ASSESSMENT}, author = {Kang, Le and Ye, Peng and Li, Yi and Doermann, David} } @article{karpathy2014deep, title = {Deep Fragment Embeddings for Bidirectional Image Sentence Mapping}, author = {Karpathy, Andrej and Joulin, Armand and Fei-Fei, Li}, journal = {arXiv preprint arXiv:1406.5679}, year = {2014} } @inproceedings{karpathy2014large, title = {Large-scale video classification with convolutional neural networks}, author = {Karpathy, Andrej and Toderici, George and Shetty, Sanketh and Leung, Thomas and Sukthankar, Rahul and Fei-Fei, Li}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2014} } @incollection{kawakami2014more, title = {More Faster Self-Organizing Maps by General Purpose on Graphics Processing Units}, author = {Kawakami, Shinji and Kamei, Keiji}, booktitle = {Soft Computing in Machine Learning}, pages = {41--51}, year = {2014}, publisher = {Springer} } @article{keyvanrad2014brief, title = {A brief survey on deep belief networks and introducing a new object oriented MATLAB toolbox (DeeBNet)}, author = {Keyvanrad, Mohammad Ali and Homayounpour, Mohammad Mehdi}, journal = {arXiv preprint arXiv:1408.3264}, year = {2014} } @article{khaligh2014you, title = {What you need to know about the state-of-the-art computational models of object-vision: A tour through the models}, author = {Khaligh-Razavi, Seyed-Mahdi}, journal = {arXiv preprint arXiv:1407.2776}, year = {2014} } @article{kielalearning, title = {Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics}, author = {Kiela, Douwe and Bottou, L{\'e}on} } @article{kim2014fully, title = {A Fully Pipelined FPGA Architecture of a Factored Restricted Boltzmann Machine Artificial Neural Network}, author = {Kim, Lok-Won and Asaad, Sameh and Linsker, Ralph}, journal = {ACM Transactions on Reconfigurable Technology and Systems (TRETS)}, volume = {7}, number = {1}, pages = {5}, year = {2014}, publisher = {ACM} } @article{kim2014handwritten, title = {Handwritten Hangul recognition using deep convolutional neural networks}, author = {Kim, In-Jung and Xie, Xiaohui}, journal = {International Journal on Document Analysis and Recognition (IJDAR)}, pages = {1--13}, year = {2014}, publisher = {Springer} } @article{kingma2013auto, title = {Auto-encoding Variational Bayes}, author = {Kingma, Diederik P and Welling, Max}, journal = {The International Conference on Learning Representations (ICLR)}, year = {2014} } @article{knowlesdeep, title = {Deep Learning for the Connectome}, author = {Knowles-Barley, Seymour and Jones, Thouis R and Morgan, Josh and Lee, Dongil and Kasthuri, Narayanan and Lichtman, Jeff W and Pfister, Hanspeter} } @article{korjusreplicating, title = {Replicating the Paper â€œPlaying Atari with Deep Reinforcement Learningâ€[MKS}, author = {Korjus, Kristjan and Kuzovkin, Ilya and Tampuu, Ardi and Pungas, Taivo} } @inproceedings{koutnik2014evolving, title = {Evolving deep unsupervised convolutional networks for vision-based reinforcement learning}, author = {Koutn{\'\i}k, Jan and Schmidhuber, Juergen and Gomez, Faustino}, booktitle = {Proceedings of the 2014 conference on Genetic and evolutionary computation}, pages = {541--548}, year = {2014}, organization = {ACM} } @incollection{koutnik2014online, title = {Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning}, author = {Koutn{\'\i}k, Jan and Schmidhuber, J{\"u}rgen and Gomez, Faustino}, booktitle = {From Animals to Animats 13}, pages = {260--269}, year = {2014}, publisher = {Springer} } @incollection{krig2014local, title = {Local Feature Design Concepts, Classification, and Learning}, author = {Krig, Scott}, booktitle = {Computer Vision Metrics}, pages = {131--189}, year = {2014}, publisher = {Springer} } @article{krizhevsky2014weirdtrick, title = {One weird trick for parallelizing convolutional neural networks}, author = {Krizhevsky, Alex}, year = {2014} } @article{langkvist2014review, title = {A review of unsupervised feature learning and deep learning for time-series modeling}, author = {L{\"a}ngkvist, Martin and Karlsson, Lars and Loutfi, Amy}, journal = {Pattern Recognition Letters}, volume = {42}, pages = {11--24}, year = {2014}, publisher = {Elsevier} } @article{lee2011unsupervised, title = {Unsupervised learning of hierarchical representations with convolutional deep belief networks}, author = {Honglak Lee and Roger Grosse and Rajesh Ranganath and A.~Y. Ng}, journal = {Communications of the ACM}, volume = {54}, number = {10}, pages = {95--103}, year = {2011}, publisher = {ACM} } @article{leung2014deep, title = {Deep learning of the tissue-regulated splicing code}, author = {Leung, Michael KK and Xiong, Hui Yuan and Lee, Leo J and Frey, Brendan J}, journal = {Bioinformatics}, volume = {30}, number = {12}, pages = {i121--i129}, year = {2014}, publisher = {Oxford Univ Press} } @incollection{li2014deep, title = {Deep learning based imaging data completion for improved brain disease diagnosis}, author = {Li, Rongjian and Zhang, Wenlu and Suk, Heung-Il and Wang, Li and Li, Jiang and Shen, Dinggang and Ji, Shuiwang}, booktitle = {Medical Image Computing and Computer-Assisted Intervention--MICCAI 2014}, pages = {305--312}, year = {2014}, publisher = {Springer} } @inproceedings{li2014large, title = {Large scale recurrent neural network on GPU}, author = {Li, Boxun and Zhou, Erjin and Huang, Bo and Duan, Jiayi and Wang, Yu and Xu, Ningyi and Zhang, Jiaxing and Yang, Huazhong}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {4062--4069}, year = {2014}, organization = {IEEE} } @article{li2014learning, title = {Learning Multi-Scale Representations for Material Classification}, author = {Li, Wenbin and Fritz, Mario}, journal = {arXiv preprint arXiv:1408.2938}, year = {2014} } @phdthesis{li2014noise, title = {Noise-Robust Speech Recognition Using Deep Neural Network}, author = {Li, Bo}, year = {2014}, school = {National University of Singapore} } @inproceedings{li2014training, title = {Training itself: Mixed-signal training acceleration for memristor-based neural network.}, author = {Li, Boxun and Wang, Yuzhi and Wang, Yu and Chen, Yiran and Yang, Huazhong}, booktitle = {ASP-DAC}, pages = {361--366}, year = {2014} } @article{liu2014pruning, title = {Pruning Deep Neural Networks by Optimal Brain Damage}, author = {Liu, Chao and Zhang, Zhiyong and Wang, Dong}, year = {2014} } @article{lopes2014machine, title = {Machine Learning for Adaptive Many-Core Machines-A Practical Approach}, author = {Lopes, Noel and Ribeiro, Bernardete}, year = {2014}, publisher = {Springer} } @article{lopes2014towards, title = {Towards adaptive learning with improved convergence of deep belief networks on graphics processing units}, author = {Lopes, Noel and Ribeiro, Bernardete}, journal = {Pattern Recognition}, volume = {47}, number = {1}, pages = {114--127}, year = {2014}, publisher = {Elsevier} } @incollection{lopes2015adaptive, title = {Adaptive Many-Core Machines}, author = {Lopes, Noel and Ribeiro, Bernardete}, booktitle = {Machine Learning for Adaptive Many-Core Machines-A Practical Approach}, pages = {189--200}, year = {2015}, publisher = {Springer} } @incollection{lopes2015deep, title = {Deep Belief Networks (DBNs)}, author = {Lopes, Noel and Ribeiro, Bernardete}, booktitle = {Machine Learning for Adaptive Many-Core Machines-A Practical Approach}, pages = {155--186}, year = {2015}, publisher = {Springer} } @incollection{lopes2015motivation, title = {Motivation and Preliminaries}, author = {Lopes, Noel and Ribeiro, Bernardete}, booktitle = {Machine Learning for Adaptive Many-Core Machines-A Practical Approach}, pages = {3--13}, year = {2015}, publisher = {Springer} } @article{lu2014analog, title = {An Analog VLSI Deep Machine Learning Implementation}, author = {Lu, Junjie}, year = {2014} } @article{lu2014surpassing, title = {Surpassing Human-Level Face Verification Performance on LFW with GaussianFace}, author = {Lu, Chaochao and Tang, Xiaoou}, journal = {arXiv preprint arXiv:1404.3840}, year = {2014} } @article{maas2014first, title = {First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs}, author = {Maas, Andrew L and Hannun, Awni Y and Jurafsky, Daniel and Ng, Andrew Y}, journal = {arXiv preprint arXiv:1408.2873}, year = {2014} } @article{maas2014increasing, title = {Increasing Deep Neural Network Acoustic Model Size for Large Vocabulary Continuous Speech Recognition}, author = {Maas, Andrew L and Hannun, Awni Y and Lengerich, Christopher T and Qi, Peng and Jurafsky, Daniel and Ng, Andrew Y}, journal = {arXiv preprint arXiv:1406.7806}, year = {2014} } @article{magnan2014sspro, title = {SSpro/ACCpro 5: Almost Perfect Prediction of Protein Secondary Structure and Relative Solvent Accessibility Using Profiles, Machine Learning, and Structural Similarity.}, author = {Magnan, Christophe N and Baldi, Pierre}, journal = {Bioinformatics}, pages = {btu352}, year = {2014}, publisher = {Oxford Univ Press} } @article{makhzani2014winner, title = {A Winner-Take-All Method for Training Sparse Convolutional Autoencoders}, author = {Makhzani, Alireza and Frey, Brendan}, journal = {arXiv preprint arXiv:1409.2752}, year = {2014} } @article{martinez2014should, title = {Should deep neural nets have ears? The role of auditory features in deep learning approaches}, author = {Martinez, Angel Mario Castro and Moritz, Niko and Meyer, Bernd T}, year = {2014} } @inproceedings{mccoppin2014deep, title = {Deep learning for image classification}, author = {McCoppin, Ryan and Rizki, Mateen}, booktitle = {SPIE Defense+ Security}, pages = {90790T--90790T}, year = {2014}, organization = {International Society for Optics and Photonics} } @article{mcgibbon2014understanding, title = {Understanding Protein Dynamics with L1-Regularized Reversible Hidden Markov Models}, author = {McGibbon, Robert T and Ramsundar, Bharath and Sultan, Mohammad M and Kiss, Gert and Pande, Vijay S}, journal = {arXiv preprint arXiv:1405.1444}, year = {2014} } @article{memiseviclearning, title = {Learning to encode motion using spatio-temporal synchrony}, author = {Memisevic, Roland} } @inproceedings{meng2014noisy, title = {Noisy training for deep neural networks}, author = {Meng, Xiangtao and Liu, Chao and Zhang, Zhiyong and Wang, Dong}, booktitle = {Signal and Information Processing (ChinaSIP), 2014 IEEE China Summit \& International Conference on}, pages = {16--20}, year = {2014}, organization = {IEEE} } @inproceedings{metze2014improved, title = {Improved audio features for large-scale multimedia event detection}, author = {Metze, Florian and Rawat, Shourabh and Wang, Yipei}, booktitle = {Multimedia and Expo (ICME), 2014 IEEE International Conference on}, pages = {1--6}, year = {2014}, organization = {IEEE} } @article{miao2014kaldi+, title = {Kaldi+ PDNN: Building DNN-based ASR Systems with Kaldi and PDNN}, author = {Miao, Yajie}, journal = {arXiv preprint arXiv:1401.6984}, year = {2014} } @article{mnih2014recurrent, title = {Recurrent Models of Visual Attention}, author = {Mnih, Volodymyr and Heess, Nicolas and Graves, Alex and Kavukcuoglu, Koray}, journal = {arXiv preprint arXiv:1406.6247}, year = {2014} } @article{momeni2014analysts, title = {Analysts' Equity Forecasts Using of Multi-layer Perception (MLP).}, author = {Momeni, Alireza and Maleki, Saber and Khajeh, Roohollah}, journal = {Advances in Environmental Biology}, volume = {8}, number = {1}, year = {2014} } @inproceedings{mousa2014single, title = {Single Image Super-resolution Reconstruction with Neural Network and Gaussian Process Regression}, author = {Mousa, Aiman M and Gao, Xinbo and Elmahalawy, Mohamed}, booktitle = {Proceedings of International Conference on Internet Multimedia Computing and Service}, pages = {386}, year = {2014}, organization = {ACM} } @article{nam2012learning, title = {Learning Sparse Feature Representations for Music Annotation and Retrievals}, author = {Nam, Juhan and Herrera, Jorge and Slaney, Malcolm and Smith, Julius}, year = {2012} } @inproceedings{ngiam2011:multimodal, title = {Multimodal Deep Learning}, author = {Ngiam, J. and Khosla, A. and Kim, M. and Nam, J. and Lee, H. and Ng, A.~Y.}, booktitle = {ICML}, year = {2011} } @article{ninaaction, title = {Action Recognition Using Ensemble of Deep Convolutional Neural Networks}, author = {Nina, Oliver and Rubiano, Carlos and Shah, Mubarak} } @article{noda2014multimodal, title = {Multimodal integration learning of robot behavior using deep neural networks}, author = {Noda, Kuniaki and Arie, Hiroaki and Suga, Yuki and Ogata, Tetsuya}, journal = {Robotics and Autonomous Systems}, volume = {62}, number = {6}, pages = {721--736}, year = {2014}, publisher = {Elsevier} } @article{nugent2014thermodynamic, title = {Thermodynamic-RAM Technology Stack}, author = {Nugent, M Alexander and Molter, Timothy W}, journal = {arXiv preprint arXiv:1406.5633}, year = {2014} } @article{ouyang2014deepid, title = {DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection}, author = {Ouyang, Wanli and Luo, Ping and Zeng, Xingyu and Qiu, Shi and Tian, Yonglong and Li, Hongsheng and Yang, Shuo and Wang, Zhe and Xiong, Yuanjun and Qian, Chen and others}, journal = {arXiv preprint arXiv:1409.3505}, year = {2014} } @inproceedings{page2014comparing, title = {Comparing Raw Data and Feature Extraction for Seizure Detection with Deep Learning Methods}, author = {Page, Adam and Turner, JT and Mohsenin, Tinoosh and Oates, Tim}, booktitle = {The Twenty-Seventh International Flairs Conference}, year = {2014} } @article{papandreou2014deep, title = {Deep Epitomic Convolutional Neural Networks}, author = {Papandreou, George}, journal = {arXiv preprint arXiv:1406.2732}, year = {2014} } @article{pascanu2014saddle, title = {On the saddle point problem for non-convex optimization}, author = {Pascanu, Razvan and Dauphin, Yann N and Ganguli, Surya and Bengio, Yoshua}, journal = {arXiv preprint arXiv:1405.4604}, year = {2014} } @inproceedings{pei2014max, title = {Max-Margin Tensor Neural Network for Chinese Word Segmentation}, author = {Pei, Wenzhe and Ge, Tao and Chang, Baobao}, booktitle = {Proceedings of ACL}, year = {2014} } @inproceedings{perotti2014neural, title = {Neural Networks for Runtime Verification}, author = {Perotti, Alan and d'Avila Garcez, Artur and Boella, Guido}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {2637--2644}, year = {2014}, organization = {IEEE} } @article{poole2014analyzing, title = {Analyzing noise in autoencoders and deep networks}, author = {Poole, Ben and Sohl-Dickstein, Jascha and Ganguli, Surya}, journal = {arXiv preprint arXiv:1406.1831}, year = {2014} } @article{qin2014deep, title = {A deep learning approach to the classification of 3D CAD models}, author = {Qin, Fei-wei and Li, Lu-ye and Gao, Shu-ming and Yang, Xiao-ling and Chen, Xiang}, journal = {Journal of Zhejiang University SCIENCE C}, volume = {15}, number = {2}, pages = {91--106}, year = {2014}, publisher = {Springer} } @article{rachmadilarge, title = {Large-Scale Scene Classification Using Gist Feature}, author = {Rachmadi, Reza Fuad and Purnama, I Ketut Eddy} } @article{rahimi2014stavicta, title = {The STAVICTA Group Report for RepLab 2014 Reputation Dimensions Task}, author = {Rahimi, Afshin and Sahlgren, Magnus and Kerren, Andreas and Paradis, Carita}, year = {2014} } @inproceedings{ramasubramanian2014spindle, title = {SPINDLE: SPINtronic deep learning engine for large-scale neuromorphic computing}, author = {Ramasubramanian, Shankar Ganesh and Venkatesan, Rangharajan and Sharad, Mrigank and Roy, Kaushik and Raghunathan, Anand}, booktitle = {Proceedings of the 2014 international symposium on Low power electronics and design}, pages = {15--20}, year = {2014}, organization = {ACM} } @article{ravanelliaudio, title = {AUDIO CONCEPT CLASSIFICATION WITH HIERARCHICAL DEEP NEURAL NETWORKS}, author = {Ravanelli, Mirco and Elizalde, Benjamin and Ni, Karl and Friedland, Gerald and Kessler, Fondazione Bruno} } @article{razavian2014cnn, title = {CNN Features off-the-shelf: an Astounding Baseline for Recognition}, author = {Razavian, Ali Sharif and Azizpour, Hossein and Sullivan, Josephine and Carlsson, Stefan}, journal = {arXiv preprint arXiv:1403.6382}, year = {2014} } @inproceedings{ribeiro2014signature, title = {Signature identification via efficient feature selection and GPU-based SVM classifier}, author = {Ribeiro, Bernardete and Lopes, Noel and Goncalves, Joao}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {1138--1145}, year = {2014}, organization = {IEEE} } @article{rieglerhough, title = {Hough Networks for Head Pose Estimation and Facial Feature Localization}, author = {Riegler, Gernot and Ferstl, David and R{\"u}ther, Matthias and Bischof, Horst} } @article{roth2014detection, title = {Detection of Sclerotic Spine Metastases via Random Aggregation of Deep Convolutional Neural Network Classifications}, author = {Roth, Holger R and Yao, Jianhua and Lu, Le and Stieger, James and Burns, Joseph E and Summers, Ronald M}, journal = {arXiv preprint arXiv:1407.5976}, year = {2014} } @incollection{roth2014new, title = {A new 2.5 D representation for lymph node detection using random sets of deep convolutional neural network observations}, author = {Roth, Holger R and Lu, Le and Seff, Ari and Cherry, Kevin M and Hoffman, Joanne and Wang, Shijun and Liu, Jiamin and Turkbey, Evrim and Summers, Ronald M}, booktitle = {Medical Image Computing and Computer-Assisted Intervention--MICCAI 2014}, pages = {520--527}, year = {2014}, publisher = {Springer} } @inproceedings{rss2013deepgrasp, title = {Deep learning for detecting robotic grasps}, author = {Lenz, Ian and Lee, Honglak and Saxena, Ashutosh}, booktitle = {Robotics: Science and Systems}, year = {2013} } @article{sainath2014parallel, title = {Parallel Deep Neural Network Training for LVCSR Tasks using Blue Gene/Q}, author = {Sainath, Tara N and Chung, I-hsin and Ramabhadran, Bhuvana and Picheny, Michael and Gunnels, John and Kingsbury, Brian and Saon, George and Austel, Vernon and Chaudhari, Upendra}, year = {2014} } @incollection{sanchez2014deep, title = {Deep Learning for Emotional Speech Recognition}, author = {S{\'a}nchez-Guti{\'e}rrez, M{\'a}ximo E and Albornoz, E Marcelo and Martinez-Licona, Fabiola and Rufiner, H Leonardo and Goddard, John}, booktitle = {Pattern Recognition}, pages = {311--320}, year = {2014}, publisher = {Springer} } @inproceedings{santos2014learning, title = {Learning Character-level Representations for Part-of-Speech Tagging}, author = {Santos, Cicero D and Zadrozny, Bianca}, booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)}, pages = {1818--1826}, year = {2014} } @inproceedings{saon2014comparison, title = {A comparison of two optimization techniques for sequence discriminative training of deep neural networks}, author = {Saon, George and Soltau, Hagen}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {5567--5571}, year = {2014}, organization = {IEEE} } @article{schmidhuber2014deep, title = {Deep Learning in Neural Networks: An Overview}, author = {Schmidhuber, J{\"u}rgen}, journal = {arXiv preprint arXiv:1404.7828}, year = {2014} } @article{schmidhuber2014draft, title = {Draft: Deep Learning in Neural Networks: An Overview}, author = {Schmidhuber, J{\"u}rgen}, year = {2014} } @article{schulzstructured, title = {Structured Prediction for Object Detection in Deep Neural Networks}, author = {Schulz, Hannes and Behnke, Sven} } @article{seide20141, title = {1-Bit Stochastic Gradient Descent and its Application to Data-Parallel Distributed Training of Speech DNNs}, author = {Seide, Frank and Fu, Hao and Droppo, Jasha and Li, Gang and Yu, Dong}, year = {2014} } @inproceedings{seide2014parallelizability, title = {On Parallelizability of Stochastic Gradient Descent for Speech DNNs}, author = {Seide, Frank and Fu, Hao and Droppo, Jasha and Li, Gang and Yu, Dong}, booktitle = {Proc. ICASSP}, year = {2014} } @inproceedings{senior2014fine, title = {Fine context, low-rank, softplus deep neural networks for mobile speech recognition}, author = {Senior, Andrew and Lei, Xin}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {7644--7648}, year = {2014}, organization = {IEEE} } @techreport{sermanet2014deep, title = {A Deep Learning Pipeline for Image Understanding and Acoustic Modeling}, author = {Sermanet, Pierre}, year = {2014} } @phdthesis{shao2014learning, title = {Learning Sparse Recurrent Neural Networks in Language Modeling}, author = {Shao, Yuanlong}, year = {2014}, school = {The Ohio State University} } @article{shen2014latent, title = {A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval}, author = {Shen, Yelong and He, Xiaodong and Gao, Jianfeng and Deng, Li and Mesnil, Gregoire}, year = {2014} } @article{sigtiaimproved, title = {Improved Music Feature Learning with Deep Neural Networks}, author = {Sigtia, Siddharth and Dixon, Simon} } @article{silberstein2014gpus, title = {GPUs: High-performance Accelerators for Parallel Applications: The multicore transformation (Ubiquity symposium)}, author = {Silberstein, Mark}, journal = {Ubiquity}, volume = {2014}, number = {August}, pages = {1}, year = {2014}, publisher = {ACM} } @article{simonmean, title = {MEAN-NORMALIZED STOCHASTIC GRADIENT FOR LARGE-SCALE DEEP LEARNING}, author = {Simon Wiesler, Alexander Richard and Schl{\"u}ter, Ralf and Ney, Hermann} } @article{simonrasr, title = {RASR/NN: THE RWTH NEURAL NETWORK TOOLKIT FOR SPEECH RECOGNITION}, author = {Simon Wiesler, Alexander Richard and Golik, Pavel and Schl{\"u}ter, Ralf and Ney, Hermann} } @article{sironi2014learning, title = {Learning Separable Filters}, author = {Sironi, Amos and Tekin, Bugra and Rigamonti, Roberto and Lepetit, Vincent and Fua, Pascal}, year = {2014}, publisher = {IEEE} } @phdthesis{slatton2014comparison, title = {A comparison of dropout and weight decay for regularizing deep neural networks}, author = {Slatton, Thomas Grant}, year = {2014} } @inproceedings{sohl2014fast, title = {Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods}, author = {Sohl-Dickstein, Jascha and Poole, Ben and Ganguli, Surya}, booktitle = {Proceedings of the 31st International Conference on Machine Learning (ICML-14)}, pages = {604--612}, year = {2014} } @inproceedings{song2014deep, title = {Deep learning for real-time robust facial expression recognition on a smartphone}, author = {Song, Inchul and Kim, Hyun-Jun and Jeon, Paul Barom}, booktitle = {Consumer Electronics (ICCE), 2014 IEEE International Conference on}, pages = {564--567}, year = {2014}, organization = {IEEE} } @article{songunsupervised, title = {Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model}, author = {Song, Xinying and He, Xiaodong and Gao, Jianfeng and Deng, Li} } @article{srivastava2014dropout, title = {Dropout: A Simple Way to Prevent Neural Networks from Overfitting}, author = {Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan}, journal = {Journal of Machine Learning Research}, volume = {15}, pages = {1929--1958}, year = {2014} } @inproceedings{stober2014classifying, title = {Classifying EEG recordings of rhythm perception}, author = {Stober, Sebastian and Cameron, Daniel J and Grahn, Jessica A}, booktitle = {15th International Society for Music Information Retrieval Conference (ISMIR'14)}, year = {2014} } @inproceedings{stober2014does, title = {Does the beat go on?: identifying rhythms from brain waves recorded after their auditory presentation}, author = {Stober, Sebastian and Cameron, Daniel J and Grahn, Jessica A}, booktitle = {Proceedings of the 9th Audio Mostly: A Conference on Interaction With Sound}, pages = {23}, year = {2014}, organization = {ACM} } @article{sukhbaatar2014learning, title = {Learning from Noisy Labels with Deep Neural Networks}, author = {Sukhbaatar, Sainbayar and Fergus, Rob}, journal = {arXiv preprint arXiv:1406.2080}, year = {2014} } @article{sun2014deep, title = {Deep learning face representation by joint identification-verification}, author = {Sun, Yi and Wang, Xiaogang and Tang, Xiaoou}, journal = {arXiv preprint arXiv:1406.4773}, year = {2014} } @inproceedings{sun2014m2c, title = {M2C: Energy efficient mobile cloud system for deep learning}, author = {Sun, Kai and Chen, Zhikui and Ren, Jiankang and Yang, Song and Li, Jing}, booktitle = {Computer Communications Workshops (INFOCOM WKSHPS), 2014 IEEE Conference on}, pages = {167--168}, year = {2014}, organization = {IEEE} } @article{sutskever2014sequence, title = {Sequence to Sequence Learning with Neural Networks}, author = {Sutskever, Ilya and Vinyals, Oriol and Le, Quoc V}, journal = {{arXiv preprint arXiv:1409.3215}, % http://arxiv.org/abs/1409.3215 year={2014}} } @article{taigman2014web, title = {Web-Scale Training for Face Identification}, author = {Taigman, Yaniv and Yang, Ming and Ranzato, Marc'Aurelio and Wolf, Lior}, journal = {arXiv preprint arXiv:1406.5266}, year = {2014} } @article{takeda2014boundary, title = {Boundary Contraction Training for Acoustic Models based on Discrete Deep Neural Networks}, author = {Takeda, Ryu and Kanda, Naoyuki and Nukaga, Nobuo}, year = {2014} } @article{tang2014hierarchical, title = {Hierarchical kernel-based rotation and scale invariant similarity}, author = {Tang, YY and Xia, Tian and Wei, Yantao and Li, Hong and Li, Luoqing}, journal = {Pattern Recognition}, volume = {47}, number = {4}, pages = {1674--1688}, year = {2014}, publisher = {Elsevier} } @article{terusaki2014emotion, title = {Emotion Detection using Deep Belief Networks}, author = {Terusaki, Kevin and Stigliani, Vince}, year = {2014} } @inproceedings{tian2014acceleration, title = {Acceleration Strategies for Speech Recognition Based on Deep Neural Networks}, author = {Tian, Chao and Liu, Jia and Peng, Zhao Meng}, booktitle = {Applied Mechanics and Materials}, volume = {556}, pages = {5181--5185}, year = {2014}, organization = {Trans Tech Publ} } @article{tingley2014towards, title = {Towards the Quantum Machine: Using Scalable Machine Learning Methods to Predict Photovoltaic Efficacy of Organic Molecules}, author = {Tingley, Michael Alan}, year = {2014} } @article{tomar2014manifold, title = {Manifold Regularized Deep Neural Networks}, author = {Tomar, Vikrant Singh and Rose, Richard C}, journal = {system}, volume = {1}, pages = {5}, year = {2014} } @article{tompson2014joint, title = {Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation}, author = {Tompson, Jonathan and Jain, Arjun and LeCun, Yann and Bregler, Christoph}, journal = {arXiv preprint arXiv:1406.2984}, year = {2014} } @article{touzetbiologically, title = {A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words}, author = {Touzet, Claude and Kermorvant, Christopher and Glotin, Herv{\'e}} } @inproceedings{tran2014learning, title = {Learning motion-difference features using Gaussian restricted Boltzmann machines for efficient human action recognition}, author = {Tran, Son N and Benetos, Emmanouil and d'Avila Garcez, Artur}, booktitle = {Neural Networks (IJCNN), 2014 International Joint Conference on}, pages = {2123--2129}, year = {2014}, organization = {IEEE} } @inproceedings{tu2014challenge, title = {Challenge Huawei challenge: Fusing multimodal features with deep neural networks for Mobile Video Annotation}, author = {Tu, Jian and Wu, Zuxuan and Dai, Qi and Jiang, Yu-Gang and Xue, Xiangyang}, booktitle = {Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on}, pages = {1--6}, year = {2014}, organization = {IEEE} } @inproceedings{turner2014deep, title = {Deep Belief Networks used on High Resolution Multichannel Electroencephalography Data for Seizure Detection}, author = {Turner, JT and Page, Adam and Mohsenin, Tinoosh and Oates, Tim}, booktitle = {2014 AAAI Spring Symposium Series}, year = {2014} } @article{van2014analysis, title = {Analysis of Deep Convolutional Neural Network Architectures}, author = {van Doorn, Joost}, year = {2014} } @inproceedings{walid2014handwritten, title = {Handwritten digit recognition using sparse deep architectures}, author = {Walid, Ragheb and Lasfar, Ali}, booktitle = {Intelligent Systems: Theories and Applications (SITA-14), 2014 9th International Conference on}, pages = {1--6}, year = {2014}, organization = {IEEE} } @inproceedings{wang2014cascaded, title = {Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection}, author = {Wang, Haibo and Cruz-Roa, Angel and Basavanhally, Ajay and Gilmore, Hannah and Shih, Natalie and Feldman, Mike and Tomaszewski, John and Gonzalez, Fabio and Madabhushi, Anant}, booktitle = {SPIE Medical Imaging}, pages = {90410B--90410B}, year = {2014}, organization = {International Society for Optics and Photonics} } @article{wang2014effective, title = {Effective Multi-Modal Retrieval based on Stacked Auto-Encoders}, author = {Wang, Wei and Ooi, Beng Chin and Yang, Xiaoyan and Zhang, Dongxiang and Zhuang, Yueting}, journal = {Proceedings of the VLDB Endowment}, volume = {7}, number = {8}, year = {2014} } @inproceedings{wang2014energy, title = {Energy efficient neural networks for big data analytics}, author = {Wang, Yu and Li, Boxun and Luo, Rong and Chen, Yiran and Xu, Ningyi and Yang, Huazhong}, booktitle = {Design, Automation and Test in Europe Conference and Exhibition (DATE), 2014}, pages = {1--2}, year = {2014}, organization = {IEEE} } @article{wang2014improving, title = {Improving Content-based and Hybrid Music Recommendation using Deep Learning}, author = {Wang, Xinxi and Wang, Ye}, year = {2014} } @inproceedings{wang2014scalable, title = {A scalable and topology configurable protocol for distributed parameter synchronization}, author = {Wang, Minjie and Zhou, Hucheng and Guo, Minyi and Zhang, Zheng}, booktitle = {Proceedings of 5th Asia-Pacific Workshop on Systems}, pages = {13}, year = {2014}, organization = {ACM} } @article{wei2014cnn, title = {CNN: Single-label to Multi-label}, author = {Wei, Yunchao and Xia, Wei and Huang, Junshi and Ni, Bingbing and Dong, Jian and Zhao, Yao and Yan, Shuicheng}, journal = {arXiv preprint arXiv:1406.5726}, year = {2014} } @incollection{westerlund2014generalized, title = {A Generalized Scalable Software Architecture for Analyzing Temporally Structured Big Data in the Cloud}, author = {Westerlund, Magnus and Hedlund, Ulf and Pulkkis, G{\"o}ran and Bj{\"o}rk, Kaj-Mikael}, booktitle = {New Perspectives in Information Systems and Technologies, Volume 1}, pages = {559--569}, year = {2014}, publisher = {Springer} } @inproceedings{wiesler2014mean, title = {Mean-normalized stochastic gradient for large-scale deep learning}, author = {Wiesler, Simon and Richard, Alexander and Schluter, Ralf and Ney, Hermann}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {180--184}, year = {2014}, organization = {IEEE} } @inproceedings{wiesler2014rasr, title = {RASR/NN: The RWTH neural network toolkit for speech recognition}, author = {Wiesler, Simon and Richard, Alexander and Golik, Pavel and Schluter, Ralf and Ney, Hermann}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {3281--3285}, year = {2014}, organization = {IEEE} } @article{wu20143d, title = {3D ShapeNets for 2.5 D object recognition and Next-Best-View prediction}, author = {Wu, Zhirong and Song, Shuran and Khosla, Aditya and Tang, Xiaoou and Xiao, Jianxiong}, journal = {arXiv preprint arXiv:1406.5670}, year = {2014} } @phdthesis{wu2014human, title = {Human Action Recognition Using Deep Probabilistic Graphical Models}, author = {Wu, Di}, year = {2014}, school = {University of Sheffield} } @article{xielearning, title = {Learning Sparse FRAME Models for Natural Image Patterns}, author = {Xie, Jianwen and Hu, Wenze and Zhu, Song-Chun and Wu, Ying Nian} } @inproceedings{xu2014cross, title = {Cross-media relevance mining for evaluating text-based image search engine}, author = {Xu, Zhongwen and Yang, Yi and Kassim, Ashraf and Yan, Shuicheng}, booktitle = {Multimedia and Expo Workshops (ICMEW), 2014 IEEE International Conference on}, pages = {1--4}, year = {2014}, organization = {IEEE} } @inproceedings{xu2014deep, title = {Deep learning of feature representation with multiple instance learning for medical image analysis}, author = {Xu, Yan and Mo, Tao and Feng, Qiwei and Zhong, Peilin and Lai, Maode and Chang, Eric I and others}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {1626--1630}, year = {2014}, organization = {IEEE} } @article{xue2014speaker, title = {Speaker adaptation of deep neural network based on discriminant codes}, author = {Xue, Shaofei and Abdel-Hamid, Ossama and Jiang, Hui and Dai, Lirong and Liu, Qingfeng}, year = {2014}, publisher = {IEEE} } @incollection{yan2014modeling, title = {Modeling Video Dynamics with Deep Dynencoder}, author = {Yan, Xing and Chang, Hong and Shan, Shiguang and Chen, Xilin}, booktitle = {Computer Vision--ECCV 2014}, pages = {215--230}, year = {2014}, publisher = {Springer} } @incollection{yang2014object, title = {Object Detection and Viewpoint Estimation with Auto-masking Neural Network}, author = {Yang, Linjie and Liu, Jianzhuang and Tang, Xiaoou}, booktitle = {Computer Vision--ECCV 2014}, pages = {441--455}, year = {2014} } @incollection{yao2014equivalence, title = {On the Equivalence Between Deep NADE and Generative Stochastic Networks}, author = {Yao, Li and Ozair, Sherjil and Cho, Kyunghyun and Bengio, Yoshua}, booktitle = {Machine Learning and Knowledge Discovery in Databases}, pages = {322--336}, year = {2014}, publisher = {Springer} } @article{yi2014shared, title = {Shared Representation Learning for Heterogeneous Face Recognition}, author = {Yi, Dong and Lei, Zhen and Liao, Shengcai and Li, Stan Z}, journal = {arXiv preprint arXiv:1406.1247}, year = {2014} } @inproceedings{you2014exploring, title = {Exploring one pass learning for deep neural network training with averaged stochastic gradient descent}, author = {You, Zhao and Wang, Xiaorui and Xu, Bo}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {6854--6858}, year = {2014}, organization = {IEEE} } @article{young2014hierarchical, title = {Hierarchical spatiotemporal feature extraction using recurrent online clustering}, author = {Young, SR and Davis, A and Mishtal, Aaron and Arel, Itamar}, journal = {Pattern Recognition Letters}, volume = {37}, pages = {115--123}, year = {2014}, publisher = {Elsevier} } @article{young2014impact, title = {On the Impact of Approximate Computation in an Analog DeSTIN Architecture}, author = {Young, Steven and Lu, Junjie and Holleman, Jeremy and Arel, Itamar}, year = {2014}, publisher = {IEEE} } @misc{yu2014exploiting, title = {Exploiting sparseness in training deep neural networks}, author = {Yu, Dong and Deng, Li and Seide, Frank Torsten Bernd and Li, Gang}, month = {apr~15}, year = {2014}, publisher = {Google Patents} } @incollection{zhang2014facial, title = {Facial Landmark Detection by Deep Multi-task Learning}, author = {Zhang, Zhanpeng and Luo, Ping and Loy, Chen Change and Tang, Xiaoou}, booktitle = {Computer Vision--ECCV 2014}, pages = {94--108}, year = {2014}, publisher = {Springer} } @inproceedings{zhang2014improving, title = {Improving deep neural networks for LVCSR using dropout and shrinking structure}, author = {Zhang, Shiliang and Bao, Yebo and Zhou, Pan and Jiang, Hui and Dai, Lirong}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {6849--6853}, year = {2014}, organization = {IEEE} } @article{zhang2014large, title = {Large-scale Deep Belief Nets with MapReduce}, author = {Zhang, KUNLEI and Chen, Xue-wen}, year = {2014}, publisher = {IEEE} } @article{zhang2014learning, title = {Learning ensemble classifiers via restricted Boltzmann machines}, author = {Zhang, Chun-Xia and Zhang, Jiang-She and Ji, Nan-Nan and Guo, Gao}, journal = {Pattern Recognition Letters}, volume = {36}, pages = {161--170}, year = {2014}, publisher = {Elsevier} } @inproceedings{zhang2014supervised, title = {Supervised deep learning with auxiliary networks}, author = {Zhang, Junbo and Tian, Guangjian and Mu, Yadong and Fan, Wei}, booktitle = {Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining}, pages = {353--361}, year = {2014}, organization = {ACM} } @article{zhao2014gpu, title = {GPU Accelerated Computation and Real-time Rendering of Cellular Automata Model for Spatial Simulation}, author = {Zhao, Yuan and Zhang, Xinchang and Zhang, Zhen and Wang, Lu and Hu, Yueming}, year = {2014}, publisher = {hgpu. org} } @article{zhaoautoencoder, title = {AN AUTOENCODER WITH BILINGUAL SPARSE FEATURES FOR IMPROVED STATISTICAL MACHINE TRANSLATION}, author = {Zhao, Bing and Tam, Yik-Cheung and Zheng, Jing} } @inproceedings{zheng2014contrastive, title = {Contrastive auto-encoder for phoneme recognition}, author = {Zheng, Xin and Wu, Zhiyong and Meng, Helen and Cai, Lianhong}, booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, pages = {2529--2533}, year = {2014}, organization = {IEEE} } @article{zhou2014deep, title = {Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction}, author = {Zhou, Jian and Troyanskaya, Olga G}, journal = {arXiv preprint arXiv:1403.1347}, year = {2014} } @article{zhu2014deep, title = {Deep learning multi-view representation for face recognition}, author = {Zhu, Zhenyao and Luo, Ping and Wang, Xiaogang and Tang, Xiaoou}, journal = {arXiv preprint arXiv:1406.6947}, year = {2014} } @article{zohrer2014single, title = {Single Channel Source Separation with General Stochastic Networks}, author = {Z{\"o}hrer, Matthias and Pernkopf, Franz}, year = {2014} } @article{zou2014generic, title = {Generic Object Detection With Dense Neural Patterns and Regionlets}, author = {Zou, Will Y and Wang, Xiaoyu and Sun, Miao and Lin, Yuanqing}, journal = {arXiv preprint arXiv:1404.4316}, year = {2014} } @article{zou2014mariana, title = {Mariana: Tencent Deep Learning Platform and its Applications}, author = {Zou, Yongqiang and Jin, Xing and Li, Yi and Guo, Zhimao and Wang, Eryu and Xiao, Bin}, journal = {Proceedings of the VLDB Endowment}, volume = {7}, number = {13}, year = {2014} }

September 19, 2014 - 7:15 am

[…] Topic-wise Deep Learning Bibliography by memkite (new) […]

September 19, 2014 - 10:05 am

[…] Deep Learning Bibliography — an annotated bibliography of recent publications (2014-) related to Deep Learning. […]

September 19, 2014 - 4:24 pm

I was unable to find a place which talked about the mathematical stack required to understand deep learning. I put one together at http://rlucente.blogspot.com/2014/08/deep-learning-mathematical-stack.html. However, I am a novice and not sure if it is correct. Please take a look and make any necessary comments.

September 22, 2014 - 9:30 pm

[…] fantastic and extensive bibliography plus github cataloging deep learning resources/code/libraries, […]

September 24, 2014 - 11:10 am

[…] Neural Networks – a Review […]

September 28, 2014 - 5:20 am

I think “A Unified Energy-Based Framework for Unsupervised Learning” is a very good theoretical paper in this field. It discusses the optimization objectives of a few unsupervised learning algorithms, including RBM and others, and how these objectives determine the properties of the solution found.

October 16, 2014 - 7:31 pm

[…] DeepLearning.University – An Annotated Deep Learning Bibliography […]

October 21, 2014 - 8:11 pm

[…] DeepLearning.University – An Annotated Deep Learning Bibliography | Memkite. […]

October 24, 2014 - 8:28 am

[…] Neural Networks: A Review […]

January 29, 2015 - 8:34 pm

[…] Learning Sparse Recurrent Neural Networks in Language Modeling […]

February 11, 2015 - 9:42 am

[…] Contrastive auto-encoder for phoneme recognition […]

November 21, 2015 - 5:47 am

[…] DeepLearning.University – An Annotated Deep Learning Bibliography | Memkite (github.com/memkite/DeepLearningBibliography) […]

December 1, 2015 - 5:32 pm

[…] Topic-wise Deep Learning Bibliography by memkite (new) […]

December 23, 2015 - 3:44 pm

[…] DeepLearning.University – An Annotated Deep Learning Bibliography | Memkite(github.com/memkite/DeepLearningBibliography) […]