Deep Learning Weekly - 🤖 - Issue #37: Facebooks AI extravaganza, Caffe2, EmojiIntelligence, MobileNets and Federated Learning

Revue
 
Hey Folks,this week Facebook is showing off their impressive deep learning based augmented reality ab
 
April 18 · Issue #37 · View online
Deep Learning Weekly
Hey Folks,
this week Facebook is showing off their impressive deep learning based augmented reality abilities and has introduced a new version of their Caffe framework. We saw an entertaining interview with Ian Goodfellow, pig-centric drawing machines and extremely lightweight MobileNets from Google and had great fun drawing emojis using Swift. Last but not least, Federated Learning allows distributed training across millions of mobile phones and MAD-GANs try to fix some shortcomings of conventional GANs.
We hope you’ll enjoy the articles as much as we did and would appreciate if you share this newsletter with your friends and colleagues. If you want to keep track of the upcoming news, take a look at our Twitter account where we share the latest announcements.
Thanks and see you next week!

Industry
Augmented reality powered by deep learning and computer vision
Google’s Dueling Neural Networks Spar to Get Smarter, No Humans Required
Teaching Machines to Draw
Learning
EmojiIntelligence: Neural Network built in Apple Playground using Swift
One-shot Learning with Memory-Augmented Neural Networks
Libraries & Code
Caffe 2
All Code Implementations for NIPS 2016 papers
Implementation of BEGAN in TensorFlow
Papers & Publications
Federated Learning: Collaborative Machine Learning without Centralized Training Data
MAD-GANs
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
A Neural Parametric Singing Synthesizer
The Reactor: A Sample-Efficient Actor-Critic Architecture
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.