https://github.com/harveyslash/sympyle

Automatic differentiation in python
https://github.com/harveyslash/sympyle

backpropagation computational-graphs deep-learning learning machine-learning neural-network tutorial

Last synced: about 1 month ago
JSON representation

Automatic differentiation in python

• Host: GitHub
• URL: https://github.com/harveyslash/sympyle
• Owner: harveyslash
• License: gpl-3.0
• Created: 2018-06-13T18:25:30.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2022-06-21T21:21:58.000Z (over 2 years ago)
• Last Synced: 2024-11-08T07:12:39.233Z (about 2 months ago)
• Topics: backpropagation, computational-graphs, deep-learning, learning, machine-learning, neural-network, tutorial
• Language: Python
• Homepage: http://harveyslash.github.io/sympyle/
• Size: 14.3 MB
• Stars: 9
• Watchers: 6
• Forks: 3
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Sympyle 

Simple Symbolic Graphs in Python

[![Build Status](https://travis-ci.com/harveyslash/sympyle.svg?branch=master)](https://travis-ci.com/harveyslash/sympyle)

[![codecov](https://codecov.io/gh/harveyslash/Sympyle/branch/master/graph/badge.svg)](https://codecov.io/gh/harveyslash/Sympyle)

[![CodeFactor](https://www.codefactor.io/repository/github/harveyslash/sympyle/badge/master)](https://www.codefactor.io/repository/github/harveyslash/sympyle/overview/master)

## About

##### Project documentation: http://harveyslash.github.io/sympyle/

Sympyle is a Python library to demonstrate the inner workings of Computational

Graphs. Computational Graphs are used by highly optimised computational

frameworks like [tensorflow](https://tensorflow.org) and

[pytorch](https://pytorch.org).

However, these frameworks make several assumptions and optimisations in order

to optimise for speed and memory. This often makes it harder to understand

the inner workings of how these libraries work.

Sympyle is a simplified model library to demonstrate the working of

computational graphs, and how

[backpropagation](https://en.wikipedia.org/wiki/Backpropagation)

works on arbitrary 'networks'.

### Examples and tutorials

All tutorials are under docs/source/tutorials and interactible at https://harveyslash.github.io/sympyle/ (under the tutorials section)