📰 Distill.pub

After five years, Distill will be taking a break.

Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.

When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings.

With diverse environments, we can analyze, diagnose and edit deep reinforcement learning models using attribution.

A collection of articles and comments with the goal of understanding how to design robust and general purpose self-organizing systems.

A closer look at how Temporal Difference Learning merges paths of experience for greater statistical efficiency

Section 3.2 of Ilyas et al. (2019) shows that training a model on only adversarial errors leads to non-trivial generalization on the original test set. We show

If we want to train AI to do what humans want, we need to study humans.

A simple and surprisingly effective family of conditioning mechanisms.

By creating user interfaces which let us work with the representations inside machine learning models, we can give people new tools for reasoning.