Deep Learning Weekly | Issue #62: Shrinking models, Google's portrait mode, DL fuelled therapist, Swish function

Bringing you everything new and exciting in the world of
 deep learning from academia to the grubby depth
 of industry every week right to your inbox. Free.

Hey and welcome to a new issue, after another news-filled week, we bring you AlphaGo's latest advance
October 23 · Issue #62 · View online
Deep Learning Weekly
Hey and welcome to a new issue,
We found a great talk on how to shrink your model, an overview on word embeddings, a tutorial on adversarial attacks, some handy Pytorch implementations of RL algorithms and a list of GAN applications. Last but not least, a new, promising activation function was found by Google Brain.
Happy hacking and reading. As always if you enjoy receiving this newsletter you can help us by sharing it with friends and colleagues.
See you later this week!

AlphaGo Zero: Learning from scratch
Andrew Ng Has a Chatbot That Can Help with Depression
Portrait mode on the Pixel 2 and Pixel 2 XL smartphones
Pornhub is using machine learning to automatically tag its 5 million videos
New Optimizations Improve Deep Learning Frameworks For CPUs
Word embeddings in 2017: Trends and future directions
Small Deep Neural Networks - Their Advantages, and Their Design
How Adversarial Attacks Work
Attention in Neural Networks and How to Use It
Introducing Variational Autoencoders (in Prose and Code)
Libraries & Code
PyTorch Implementation of several Reinforcement Learning Algorithms
Papers & Publications
Swish: a Self-Gated Activation Function
Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains its Predictions
SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes