Hi! New AI Weekly is here! Enjoy your weekend reading AI news and don’t forget to share it with your friends 😉
Google’s AutoML: Cutting Through the Hype
Nuts and Bolts of WGANs, Kantorovich-Rubistein Duality, Earth Movers Distance
Ultimate Guide to Getting Started with Tensorflow
AlphaGo Zero demystified
Learning Dexterous In-Hand Manipulation – OpenAI use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which they randomize many of the physical properties of the system like friction coefficients and an object’s appearance. Their policies transfer to the physical robot despite being trained entirely in simulation. This method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity.
Tagged Anime Illustrations – more than 300,000 pieces of fan art