BayesNewton

Deep Learning for humans

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

? A ranked list of awesome machine learning Python libraries. Updated weekly.

Convert Machine Learning Code Between Frameworks

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Trax — Deep Learning with Clear Code and Speed

Python code for "Probabilistic Machine learning" book by Kevin Murphy

Flax is a neural network library for JAX that is designed for flexibility.

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

A highly efficient implementation of Gaussian Processes in PyTorch