Someone has entered an AI in a Japanese mayoral race

Gift of Garb: How AI Helps Fashion Followers Choose the Best Dress

Towards a Virtual Stuntman

Motion control problems have become standard benchmarks for reinforcement learning, and deep RL methods have been shown to be effective for a diverse suite of tasks ranging from manipulation to locomotion. However, characters trained with deep RL often exhibit unnatural behaviours, bearing artifacts such as jittering, asymmetric gaits, and excessive movement of limbs. Can we train our characters to produce more natural behaviours?

Depthwise separable convolutions for machine learning

Convolutions are an important tool in modern deep neural networks (DNNs). This post is going to discuss some common types of convolutions, specifically regular and depthwise separable convolutions. My focus will be on the implementation of these operation, showing from-scratch Numpy-based code to compute them and diagrams that explain how things work.