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 up
Pinned repositories
Repositories
-
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
-
-
open-covid-19-data
Open source aggregation pipeline for public COVID-19 data, including hospitalization/ICU/ventilator numbers for many countries.
-
tensor2robot
Distributed machine learning infrastructure for large-scale robotics research
-
dex-lang
Research language for array processing in the Haskell/ML family
-
bert
TensorFlow code and pre-trained models for BERT
-
tapas
End-to-end neural table-text understanding models.
-
tiny-differentiable-simulator
Tiny Differentiable Simulator is a header-only C++ physics library with zero dependencies.
-
simclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
-
morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
-
dreamer
Dream to Control: Learning Behaviors by Latent Imagination
-
language
Shared repository for open-sourced projects from the Google AI Language team.
-
seed_rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
-
albert
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
-
rigl
End-to-end training of sparse deep neural networks with little-to-no performance loss.
-
arxiv-latex-cleaner
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
-
computation-thru-dynamics
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
-
torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
-
recsim
A Configurable Recommender Systems Simulation Platform
-
dads
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
-
fast-soft-sort
Fast Differentiable Sorting and Ranking
-
reassessed-imagenet
Labels and other data for the paper "Are we done with ImageNet?"
-
noisystudent
Code for Noisy Student Training. https://arxiv.org/abs/1911.04252