ad-kernels

A highly efficient implementation of Gaussian Processes in PyTorch

Fast and Easy Infinite Neural Networks in Python

Source-to-Source Debuggable Derivatives in Pure Python

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

Gaussian processes in TensorFlow

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Brian is a free, open source simulator for spiking neural networks.

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

DiffSharp: Differentiable Functional Programming