An experimental open-source attempt to make GPT-4 fully autonomous.

Graph Nets in pytorch

OpenVINO™ Toolkit repository

A website (will be lczero.org)

A scalable physics engine implemented with JAX. With JIT batteries 🔋

A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs

A collection of high-quality models for the MuJoCo physics engine, curated by DeepMind.

UCL ARC computational statistics and machine learning reading group

Playing around with stable diffusion. Generated images are reproducible because I save the metadata and latent information. You can generate and then later interpolate between the images of your ch…

UCI chess engine

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

JAX-based neural network library

All study notes and guides for the futureproof curriculum

scikit-learn: machine learning in Python

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An Open Source Machine Learning Framework for Everyone

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

The Abstraction and Reasoning Corpus

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

COMP0104 - Lab08a

Baseline for the Conala: Code/Natural Language Challenge

UCL Module: Introduction to Deep Learning

A fairly strong Go/Baduk/Weiqi playing program

TensorFlow Reinforcement Learning

Code accompanying "Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks"

Code and other material for the book "Deep Learning and the Game of Go"