Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.
-
Updated
Jan 7, 2026 - Python
Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.
Drop-in autodiff for NumPy.
XLuminA, a highly-efficient, auto-differentiating discovery framework for super-resolution microscopy.
A toy deep learning framework implemented in pure Numpy from scratch. Aka homemade PyTorch lol.
Yaae: Yet another autodiff engine (written in Numpy).
A differentiable underwater vehicle dynamics.
Experiments with forward gradients on optimization test functions
Assignments for Data Intensive Systems for Machine Learning Coursework
Fork of Matt Loper's autodifferentiation framework for Python
Dualitic is a Python package for forward mode automatic differentiation using dual numbers.
Tiny automatic differentiation (autodiff) engine for NumPy tensors implemented in Python.
Autograd: is a lightweight Python engine for automatic differentiation and neural networks, providing a clear, educational implementation of backpropagation and computational graphs.
Yet another tensor automatic differentiation framework
ToyDL: Deep Learning from Scratch
PyPIC3D is a 3D particle-in-cell code written in Python using Jax.
A toy forward-mode autodiff utility written in Python
A simple library for building computational graphs with autodiff support.
A brief (and inaccurate) history of derivatives, with a brief (and incomplete) Python implementation
zapnAD: An auto-differentiation package.
Add a description, image, and links to the autodifferentiation topic page so that developers can more easily learn about it.
To associate your repository with the autodifferentiation topic, visit your repo's landing page and select "manage topics."