Bayesian negative sampling is the theoretically optimal negative sampling algorithm that runs in linear time.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Reference models and tools for Cloud TPUs.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR2020)

Quantization-aware training in Pytorch

StyleGAN2 - Official TensorFlow Implementation

Face Analysis Project on MXNet

StyleGAN - Official TensorFlow Implementation

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Implement AlphaZero/AlphaGo Zero methods on Chinese chess.

An asynchronous/parallel method of AlphaGo Zero algorithm with Gomoku

An implementation of skip-thought vectors in Tensorflow

Progressive Growing of GANs for Improved Quality, Stability, and Variation

TensorFlow code and pre-trained models for BERT

An implementation of improved AlphaGo algorithm in the game of Gomoku.