reverse-mode-ad

Here is 1 public repository matching this topic...

rukmini-17 / mini-autodiff

A lightweight, reverse-mode Automatic Differentiation (AD) engine built from scratch using Python and NumPy. Supports dynamic computational graphs and complex linear algebra operations.

python machine-learning calculus numpy automatic-differentiation mathematics autograd backpropagation scratch-implementation differentiable-programming ml-systems computational-graph reverse-mode-ad

Updated Dec 24, 2025
Jupyter Notebook

Improve this page

Add a description, image, and links to the reverse-mode-ad topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the reverse-mode-ad topic, visit your repo's landing page and select "manage topics."

Learn more

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

reverse-mode-ad

Here is 1 public repository matching this topic...

rukmini-17 / mini-autodiff

Improve this page

Add this topic to your repo