ML Anthology

Distill 2019

8 papers

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features' Logan Engstrom, Justin Gilmer, Gabriel Goh, Dan Hendrycks, Andrew Ilyas, Aleksander Madry, Reiichiro Nakano, Preetum Nakkiran, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, Eric Wallace
Code
A Visual Exploration of Gaussian Processes Jochen Görtler, Rebecca Kehlbeck, Oliver Deussen
Code
Activation Atlas Shan Carter, Zan Armstrong, Ludwig Schubert, Ian Johnson, Chris Olah
Code
AI Safety Needs Social Scientists Geoffrey Irving, Amanda Askell
Code
Computing Receptive Fields of Convolutional Neural Networks André Araujo, Wade Norris, Jack Sim
Code
Open Questions About Generative Adversarial Networks Augustus Odena
Code
The Paths Perspective on Value Learning Sam Greydanus, Chris Olah
Code
Visualizing Memorization in RNNs Andreas Madsen
Code