|November 2 · Issue #13 · View online |
There is lots of great code in this week’s issue from image annotation and enhancement to bleeding edge deep learning set-ups on AWS AMI, if you are looking for something to hack away at this week you should be well served.
As always if you enjoy receiving this newsletter, please considering sharing it with friends and colleagues, your support is very much appreciated.
| AI Pioneer Yoshua Bengio Is Launching Element AI, a Deep-Learning Incubator |
One of the founding fathers of the deep learning movement is building a Silicon Valley-style tech incubator for AI in Montreal.
| How AI Is Shaking Up the Chip Market |
Companies are investing in specialized hardware for Deep Learning to speed up training and inference.
| Microsoft releases beta of Microsoft Cognitive Toolkit for deep learning advances |
Microsoft has released an updated version of Microsoft Cognitive Toolkit, a system for deep learning that is used to speed advances in areas such as speech and image recognition and search relevance on CPUs and NVIDIA® GPUs.
| The AI Revolution: Why Deep Learning Is Suddenly Changing Your Life |
AI and deep machine learning are electrifying the computing industry and will soon transform corporate America.
| DeepDrive an Open Platform for Autonomous Driving |
DeepDrive aims to be the Linux of Postgres of self-driving cars, an open platform in a field dominated by sealed off industry players.
| Research Blog: How Google Translate squeezes deep learning onto a phone |
The new Google Translate app is powered by deep learning, how does google enable their service to work offline given the hardware constraints of mobile devices?
| Hugo Larochelle's neural network & deep learning tutorial videos, subtitled & screengrabbed ~ prooffreader plus |
David Taylor (@prooffreader) took the time to turn Hugo Larochelle’s lecture from the Deep Learning Summer School in Montreal into a slide deck using youtube subtitles and screengrabs for all of us who prefer reading to watching a video.
| Optimizing the hyperparameter of which hyperparameter optimizer to use |
A comparison of two open-source packages for hyperparameter optimization, Hyperopt and scikit-optimize.
| GitHub - tzutalin/labelImg: LabelImg is a graphical image annotation tool |
LabelImg: a graphical image annotation tool.
| GitHub - Miej/GoDeeper |
A simul-build of all of the latest, bleeding-edge packages for deep learning
| GitHub - RecurrentHighwayNetworks |
This repository contains code accompanying the paper Recurrent Highway Networks (RHNs). RHNs are an extension of Long Short Term Memory Networks with forget gates to enable the learning of deep recurrent state transitions.
| neural-enhance/README.rst at master · alexjc/neural-enhance · GitHub |
neural-enhance - Super Resolution for images using deep learning.
| Learning Scalable Deep Kernels with Recurrent Structure |
Many applications in speech, robotics, finance, and biology deal with sequential data, where ordering matters and recurrent structures are common. However, this structure cannot be easily captured by standard kernel functions. To model such structure, we propose expressive closed-form kernel functions for Gaussian processes.
| Neural Machine Translation in Linear Time |
Introduces The ByteNet a stack of two dilated convolutional neural networks which runs in time that is linear in the length of the sequences and preserves the sequences’ temporal resolution.
| Research Blog: Supercharging Style Transfer |
Learning and combining multiple styles for neural style.