Reinforcement Learning

Learning from humans: what is inverse reinforcement learning?

Jordan Alexander

Call for Ideas - June 2018

The Gradient
Generative Models

How AI learned to be creative

Shreya Shankar
Vision

Going beyond the bounding box with semantic segmentation

Andy Chen, Chaitanya Asawa
Language

Speech recognition systems are now vulnerable to adversarial attacks

Hugh Zhang
Graphs

How do we capture structure in relational data?

Matthew Das Sarma
Overviews

What does it really mean for an algorithm to be biased?

Eric Wang

The Gradient: A Note from the Editors

The Gradient