Autodifferentiation GitHub Repositories

automatic differentiation made easier for C++

Deep learning in Rust, with shape checked tensors and neural networks

Tensors and dynamic neural networks in pure Rust.

Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.

Fast, easy automatic differentiation in C++

Drop-in autodiff for NumPy.

FastAD is a C++ implementation of automatic differentiation both forward and reverse mode.

XLuminA, a highly-efficient, auto-differentiating discovery framework for super-resolution microscopy.

Differentiate python calls from Julia

200行写一个自动微分工具

Fazang is a Fortran library for reverse-mode automatic differentiation, inspired by Stan/Math library.

A toy deep learning framework implemented in pure Numpy from scratch. Aka homemade PyTorch lol.

Yaae: Yet another autodiff engine (written in Numpy).

Forward mode automatic differentiation for Fortran

A differentiable underwater vehicle dynamics.

A minimalist neural networks library built on a tiny autograd engine

JAX Tutorial notebooks : basics, crash & tips, usage of optax/JaxOptim/Numpyro

Algorithmic differentiation with hyper-dual numbers in C++ and Python

A rust implementation of Andrej Karpathy's Micrograd

C++20 numerical and analytical derivative computations

Scala embedded universal probabilistic programming language

There's more to JAX.

Experiments with forward gradients on optimization test functions

Assignments for Data Intensive Systems for Machine Learning Coursework

Automatic differentiation: A tool that allows you to calculate multivariable equations, vectors, matrices, and more. All done in C++, no libraries!

F-1 method

A tiny autograd library made for educational purposes.

A lightweight autograd engine inspired by PyTorch and micrograd