Grow your team on GitHub
GitHub is home to over 50 million developers working together. Join them to grow your own development teams, manage permissions, and collaborate on projects.
Sign upRepositories
-
bleurt
BLEURT is a metric for Natural Language Generation based on transfer learning.
-
augmix
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
-
batch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
-
reverse-engineering-neural-networks
A collection of tools for reverse engineering neural networks.
-
language
Shared repository for open-sourced projects from the Google AI Language team.
-
episodic-curiosity
Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability
-
dads
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
-
computation-thru-dynamics
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
-
bert
TensorFlow code and pre-trained models for BERT
-
albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
-
ssl_detection
Semi-supervised learning for object detection
-
planet
Learning Latent Dynamics for Planning from Pixels
-
big_transfer
Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.
-
seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.