Go to Top

Memkite

Continuous Integration for testing Metal GPGPU shaders for iOS with Swig, Numpy and Python

Apple Inc’s Metal is an alternative to OpenGL for graphics processing on iPhone and iPad, but it also supports general purpose data-parallel programming for GPUs (i.e. GPGPU programming) it is an alternative to OpenCL and Nvidia’s Cuda. The Metal shading language is based on the C++11 Specification [PDF] with specific extensions and restrictions, but one challenge with Metal is …Read More

Treadmill Desks – the Future Software Engineer Office Rig?

Apple’s CEO Tim Cook described sitting as the new cancer, and using a treadmill desk is perhaps the easiest way of reducing the amount of sitting – at least in an office environment. As most novel technologies treadmill desks has the classic celebrity endorsement (Victoria Beckham), and is expected to become a unicorn billion dollar business as it enters the …Read More

Deeplearning.University – Bibliographies from Lisa Labs (Yoshua Bengio’s lab)

Today I’m honored to publish two high quality Deep Learning related bibliographies (in Bibtex) from Lisa Labs at University of Montreal in Canada. These bibliographies will improve Deeplearning.University a lot wrt quality and coverage (in the next update), but here they are in unaltered form available at github: 1. Bibtex for papers published by Lisa Labs (624 bibtex …Read More

Update with 29 new publications to Deeplearning.University Bibliography

I’ve gone from infrequent (monthly’ish) to the Deeplearning.University Bibliography to more frequent updates (1-2 times per week). Underneath are 29 new deep learning papers since last update (8 days prior to this). There are many highly interesting papers, and I would in particular like to point out: Transferring Knowledge from a Rnn to a Dnn Tree-based Convolution: …Read More

Update with 13 new papers to Deeplearning.University

Links to Deep Learning Subtopics [acoustic][acoustic model][cognition][embedded][feature][linear model][linear models][overview][regression][review][search][social][speech][speech recognition][survey][theory][visual] Acoustic Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends   Acoustic Model Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends   Cognition Deep learning approaches …Read More

Update with 57 papers to Deeplearning.University Bibliography

This update to Deeplearning.University has 57 new Deep Learning papers (all from 2015) collected in the period since last update (March 29th, 2015) and until today.  See the 57 new papers below. As always if you want have suggestions to the bibliography (in particular: improved Bibtex-entries or additions), please do that as git pull-requests on the file:https://github.com/memkite/DeepLearningBibliography/blob/master/bibtex/deeplearninggpuwithkeywords2014.bib …Read More

Update with 362 new publications to Deeplearning.University Bibliography

This update to Deeplearning.University has 362 new Deep Learning papers (all from 2015) collected in the period since last update (January 27th, 2015) and until today.  See the 362 new papers below, and deeplearning.university for the entire updated bibliography (it has more than 1000 papers now, 1324 to be accurate). As always if you want …Read More

Deep Learning for Speech Recognition

This blog post gives a brief overview of recent Deep Learning for Speech Recognition (NLP) publications sampled from the Speech Recognition category published on http://deeplearning.university – See also previous posting on Deep Learning for Natural Language Processing (NLP). Best regards, Amund Tveit Acoustic Modeling Increasing Deep Neural Network Acoustic Model Size for Large Vocabulary Continuous Speech Recognition Deep …Read More

Deep Learning for Natural Language Processing

This blog post gives a brief overview of recent deep learning for Natural Language Processing (NLP) publications sampled from the NLP category published on http://deeplearning.university (see also follow-up blog post on Deep Learning for Speech Recognition) (disclaimer: this was quickly put together for a local workshop, but hopefully useful) Best regards, Amund Tveit Sentiment Analysis Adaptive multi-compositionality for …Read More

Update with 408 recent papers to Deeplearning.University

It has been a while (November 2014) since our last update to the deeplearning bibliography at http://deeplearning.university – but underneath is an update with 408 recent papers (late 2014/early 2015). (This update combined with existing papers will be published to deeplearning.university shortly) Best regards, Amund Tveit (twitter.com/atveit – amund@memkite.com) Links to Deep Learning Subtopics [3d] …Read More

Example of Sharing Memory between GPU and CPU with Swift and Metal for iOS8

1. Background In two prior postings I presented i) data-parallel Swift/Metal example and ii) benchmark (compared to Accelerate) of how to use Swift combined with Metal for General Purpose GPU based processing on iOS8 devices (e.g. iPhone and iPad), this posting extends those by showing how use shared memory between GPU and CPU with Swift …Read More

GPGPU Performance of Swift/Metal vs Accelerate on iPhone 6 & 5S, iPad Air and iPad Mini

1. Background In a prior posting I presented how to use Swift combined with Metal for General Purpose GPU based processing, this posting presents related benchmarks – compared to using the Accelerate Framework – on iPhone 5S, iPhone 6, iPad Air and iPad Mini. All Swift/Metal and Accelerate code and benchmarks can be found at …Read More

Data-Parallel Programming with Metal and Swift for iPhone/iPad GPU

Apple describes Metal as: “Metal provides the lowest-overhead access to the GPU, enabling you to maximize the graphics and compute potential of your iOS 8 app. With a streamlined API, precompiled shaders, and support for efficient multi-threading, Metal can take your game or graphics app to the next level of performance and capability.” – source: …Read More

Added 152 new Deep Learning Publications to the Bibliography

Added 152 new Deep Learning papers to the Deeplearning.University Bibliography, if you want to see them separate from the previous papers in the bibliography the new ones are listed below. There are many very interesting papers, e.g. in the medicine (e.g. deep learning for cancer-related analysis such as mammogram and pancreas cancer, and heart diseases), …Read More

List of 75 Most Popular Deep Learning Papers in the Bibliography

A month ago we published a blog post showing the 20 most popular Deep Learning papers in the bibliography,  this time we’re showing the 75 most popular Deep Learning papers in the list below. Note that this blog post (and the other blog posts) and the deep learning bibliography itself is available on github: github.com/memkite/DeepLearningBibliography …Read More

Updates to the Deep Learning Bibliography from Li Dong (and Knut O. Hellan

We’re of course grateful for updates with new bibliography entries to the Deep Learning Bibliography from researchers and practitioners in the field (note: we don’t mind if you suggest your own papers to the bibliography as long as they are within deep learning). The update with new bibliography entries today is suggested by Li Dong (State Key Lab …Read More

Update with 162 new papers to Deeplearning.University Bibliography

Added 162 new Deep Learning papers to the Deeplearning.University Bibliography, if you want to see them separate from the previous papers in the bibliography the new ones are listed below. There are many highly interesting papers, a few examples are: Deep neural network based load forecast – forecasts of electricity prediction The relation of eye …Read More