.. Nanograd documentation master file, created by
   sphinx-quickstart on Thu Feb  6 13:46:18 2025.
   You can adapt this file completely to your liking, but it should at least
   contain the root `toctree` directive.

Nanograd documentation
======================

Nanograd-bgriebel is a scalar automatic differentiation engine, with a neural
network api similar to PyTorch. It uses reverse mode automatic differentiation 
to calculate gradients, allowing for gradient descent based training of neural 
networks. Nanograd-bgriebel is based on Andrej Karpathy's `micrograd`_.

.. _micrograd: https://github.com/karpathy/micrograd


.. toctree::
   :maxdepth: 2
   :caption: Contents:
  
   engine
   nn