Deep Learning Weekly - Issue #19: NIPS2016 retrospective, deep learning study group & better hearing aids

Revue
 
Howdy,NIPS 2016 seems to have been a huge blast, this week's issue features lots of retrospectives, t
 
December 13 - Issue #19
Deep Learning Weekly
Howdy,

NIPS 2016 seems to have been a huge blast, this week’s issue features lots of retrospectives, tutorials, and code from the conference for those of us who couldn’t make it.
In this issue we’ll also see how deep learning improves hearing aids, DeepMind shows us how to implement their learning to learn paper, we’ll learn how to train GANs and much more…

Happy reading!

PS: We published a wildly popular open-source deep learning curriculum this week and have decided to create a Slack group to facilitate exchange and discussion of the materials. You can join us here.

Industry
AMD launches Radeon Instinct GPUs to tackle deep learning, artificial intelligence
The major advancements in Deep Learning in 2016
Deep Learning Reinvents the Hearing Aid
The Audi Q2 Deep Learning Concept Car
Machined Learnings: NIPS 2016 Reflections
Learning
Experiments in Handwriting with a Neural Network
Deep Learning Cheat Sheet
Richard Socher on the future of Deep Learning
Machine Learning Yearning
Tutorials from NIPS 2016
GANhacks or "How to Train a GAN?"
Libraries & Code
tiny-dnn a tiny Deep Learning Framework in C++
DeepMind's Learning to Learn in TensorFlow
Papers & Publications
Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
Predicting Brain Age with Deep Learning from raw Imaging Data
Spatially Adaptive Computation Time for Residual Networks
Jobs
Research Scientist, Google Brain
Did you enjoy this issue?
Thumbs up 1ae5a7bdfcd3220e2b376aa0c1607bc5edaba758e5dd83b482d03965219a220b Thumbs down e13779fa29e2935b47488fb8f82977fedcf689a0cc0cc3c19fa3c6bb14d1493b
Carefully curated by Deep Learning Weekly with Revue.
If you were forwarded this newsletter and you like it, you can subscribe here.
If you don't want these updates anymore, please unsubscribe here.