A game theoretic approach to explain the output of any machine learning model.

Visualizations for machine learning datasets

An annotated implementation of the Transformer paper.

An adversarial example library for constructing attacks, building defenses, and benchmarking both

A collection of infrastructure and tools for research in neural network interpretability.

Demonstrations of Magenta Models

Lab materials for the Full Stack Deep Learning Course

Code for "High-Precision Model-Agnostic Explanations" paper

A few notebooks about deep learning in pytorch

Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"

This repository contains the full code for the "Towards fairness in machine learning with adversarial networks" blog post.