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

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Lab materials for the Full Stack Deep Learning Course

Python library for Multi-Armed Bandits

The BlazeFace face detector model implemented in PyTorch

The code repository for examples in the O'Reilly book 'Generative Deep Learning' using Pytorch

A minimal implementation of autograd (in pure Python) 🍰