Python package built to ease deep learning on graph, on top of existing DL frameworks.

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Scalable fuzzing infrastructure.

High level Python client for Elasticsearch

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

🏭 Collaboratively build, visualize, and design neural nets in browser

An information security preparedness tool to do adversarial simulation.

Neural relational inference for interacting systems - pytorch

人人网小黄鸡 (deprecated)

An open source project to document AI progress through data.

PyTorch code to run synthetic experiments.

Code for "The Reversible Residual Network: Backpropagation Without Storing Activations"

TensorFlow on Spark

Resource Management with Deep Reinforcement Learning (HotNets '16)

Deep neural network kernel for Gaussian process

Command-line tool for accessing Scalyr services

Lots of metrics for quantifying gerrymandering.