Autodifferentiation Python Packages

uncertainties

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

jaxmore

There's more to JAX.

hyperjet

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

mygrad

Drop-in autodiff for NumPy.

hypergraph

Reversed mode second order automatic differentiation for python (WIP)

pyfit

A minimalist neural networks library built on a tiny autograd engine

jax-bounded-while

There's more to JAX.

metabochumpy

Fork of Matt Loper's autodifferentiation framework for Python

toydl

ToyDL: Deep Learning from Scratch

xlumina

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

nanograd-lite

Automatic differentiation engine built from scratch using only numpy with computational graphs and backpropagation.

zapnad

zapnAD: An auto-differentiation package.