Docs

Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/CPU.

Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

📚 Papers & articles of companies sharing their work on applied data science & machine learning.

Python package facilitating the use of Bayesian Deep Learning methods with Variational Inference for PyTorch

Hummingbird compiles trained ML models into tensor computation for faster inference.

Implementation of the variational continual learning method

Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.

Deep universal probabilistic programming with Python and PyTorch

Express & compile probabilistic programs for performant inference on CPU & GPU. Powered by JAX.

An interactive deep learning book with code, math, and discussions, based on the NumPy interface.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Machine Learning interview prep guide

JAX-based neural network library

A collection of infrastructure and tools for research in neural network interpretability.

Alternative to TensorFlow2/Keras/PyTorch for more concise, robust and optimized deep learning code

Uplift modeling and causal inference with machine learning algorithms

Tools for the symbolic manipulation of PyMC models, Theano, and TensorFlow graphs.

Enabling PyTorch on Google TPU

A lightweight probabilistic programming language in NumPy or TensorFlow.

A high-level probabilistic programming interface for TensorFlow Probability

Easy and Fast Infinite Neural Networks in Python

Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand tuning

Minimalist implementation of VQ-VAE in Pytorch

Probabilistic reasoning and statistical analysis in TensorFlow