distill.pubadded August 2026
Distillby Alexander Mordvintsev; Nicola Pezzotti; Ludwig Schubert; Chris Olah25 Jul 2018
A powerful, under-explored tool for neural network visualizations and art. Neural networks trained to classify images have a remarkable — and surprising! — capacity to generate images.
Distillby Vincent Dumoulin; Ethan Perez; Nathan Schucher; Florian Strub; Harm de Vries; Aaron Courville; Yoshua Bengio9 Jul 2018
A simple and surprisingly effective family of conditioning mechanisms. Many real-world problems require integrating multiple sources of information.
Distillby Chris Olah; Arvind Satyanarayan; Ian Johnson; Shan Carter; Ludwig Schubert; Katherine Ye; Alexander Mordvintsev6 Mar 2018
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them — and the rich structure of this combinatorial space.
Distillby Shan Carter; Michael Nielsen4 Dec 2017
By creating user interfaces which let us work with the representations inside machine learning models, we can give people new tools for reasoning.
Distillby Awni Hannun27 Nov 2017
A visual guide to Connectionist Temporal Classification, an algorithm used to train deep neural networks in speech recognition, handwriting recognition and other sequence problems.
Distillby Chris Olah; Alexander Mordvintsev; Ludwig Schubert7 Nov 2017
How neural networks build up their understanding of images There is a growing sense that neural networks need to be interpretable to humans.
Distillby Gabriel Goh4 Apr 2017
Here’s a popular story about momentum [1, 2, 3]: gradient descent is a man walking down a hill. He follows the steepest path downwards; his progress is slow, but steady.
Distillby Chris Olah; Shan Carter22 Mar 2017
Achieving a research-level understanding of most topics is like climbing a mountain. Aspiring researchers must struggle to understand vast bodies of work that came before them, to learn techniques...
Distillby Shan Carter; David Ha; Ian Johnson; Chris Olah6 Dec 2016
Neural networks are an extremely successful approach to machine learning, but it’s tricky to understand why they behave the way they do.
Distillby Augustus Odena; Vincent Dumoulin; Chris Olah17 Oct 2016
When we look very closely at images generated by neural networks, we often see a strange checkerboard pattern of artifacts.
8%