Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models

skscope: Sparse-Constrained OPtimization via itErative-solvers

AutoDiff DAG constructor, built on numpy and Cython. A Neural Turing Machine and DeepQ agent run on it. Clean code for educational purpose.

Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.

Unitful Quantities in JAX

Galactic and Gravitational Dynamics in Python (+ GPU and autodiff)

Differentiable Gaussian Process implementation for PyTorch

A modern astrodynamics library powered by JAX: differentiate, vectorize, JIT to GPU/TPU, and more

A pytoch-like autograd engine.

Code for "Joint Modeling of Quasar Variability and Accretion Disk Reprocessing using Latent Stochastic Differential Equation"

Differentiable tensor renormalization group

Library for auto differentiation based purely on NumPy

MicrogradPlus is an educational project aiming to provide a simple, yet extensible, NumPy-based automatic differentiation library.

Neural Network library made with numpy

A lightweight auto-differentiation and backpropagation library written in python using numpy.

Calculates partial derivatives of an input function.

autoD is a lightweight, flexible automatic differentiation for python3 based on numpy.