Implementation of the supervised learning experiments in Vector-based navigation using grid-like representations in artificial agents, as published at https://www.nature.com/articles/s41586-018-0102-6

PyTorch original implementation of Cross-lingual Language Model Pretraining.

hanabi_learning_environment is a research platform for Hanabi experiments.

Logistic Circuits

Keras Temporal Convolutional Network. Supports Python and R.

Linguistically-Informed Self-Attention implemented in TensorFlow

Meta learning for Neural Machine Translation

Tensorflow implementation of contextualized word representations from bi-directional language models

Repository for paper "SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference"

A python tool for evaluating the quality of sentence embeddings.

Pytorch implementation of LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS (BigGAN)

Implementation of Everybody Dance Now by pytorch

Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]

Pytorch implementation of group normalization in https://arxiv.org/abs/1803.08494 (Following the PyTorch Style)

Style transfer, deep learning, feature transform

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Extract data from a wide range of Internet sources into a pandas DataFrame.

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

Data Science Using Python

Keras package for deep residual networks

Reference implementations of popular deep learning models.

Residual networks implementation using Keras-1.0 functional API

The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.

ChatterBot is a machine learning, conversational dialog engine for creating chat bots

TensorFlow code for the neural network presented in the paper: "code2vec: Learning Distributed Representations of Code"