Deep Learning Weekly - Issue #100: TensorFlow Dev Summit, AI Art, MMO Reinforcement Learning, Google Duplex, Figure Eight, DeepFashion2, and more…

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.

 
As you might have noticed, after 99 issues, Deep Learning Weekly has been on hiatus for the last few
 
March 13 · Issue #100 · View online
Deep Learning Weekly
As you might have noticed, after 99 issues, Deep Learning Weekly has been on hiatus for the last few months.
Talk about a cliffhanger.
But we’re back with issue #100! This week, we dive into highlights from this year’s TensorFlow Dev Summit, the blurry lines between art and tech, a new OpenAI release, and the implications of a major acquisition. Additionally, we’ll learn about an emerging deep learning architecture and take a look at “The Lottery Hypothesis”, reinforcement learning on Atari, and much more.
We’ve also got some news of our own. Deep Learning Weekly has joined Heartbeat, a like-minded community of ML enthusiasts that shares the same values and mission. You can read more about this new partnership here. As you’ll see below, not much else is changing. We’ll still deliver all the latest and greatest deep learning news, industry updates, tutorials, code, and more each week.
As always, happy reading and hacking.
See you next week!

Industry
TensorFlow Dev Summit
The AI-Art Gold Rush Is Here
OpenAI Releases Neural MMO
Google Duplex is coming to 43 states and iPhones
Appen acquires Figure Eight for up to $300M, bringing two data annotation companies together – TechCrunch
Learning
How Transformers Work
Teaching an AI to Draft Magic: the Gathering – Towards Data Science
Foundations Built for a General Theory of Neural Networks | Quanta Magazine
Best of Machine Learning
Libraries & Code
GitHub - zphang/bert_on_stilts: BERT on STILTS
GitHub - zjhuang22/maskscoring_rcnn: Codes for paper "Mask Scoring R-CNN".
Datasets
GitHub - switchablenorms/DeepFashion2
Papers & Publications
[1903.01611] The Lottery Ticket Hypothesis at Scale
[1903.00374] Model-Based Reinforcement Learning for Atari