Skip to content

A very small and very slow "deep learning framework." Likely useless for anything other than educational purposes.

Notifications You must be signed in to change notification settings

mvoelske/diy-autodiff

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Automatic Differentiation from Scratch in Python

This repository contains an extremely basic machine learning framework with automatic differentiation in a couple lines of plain Python.

With inspiration from [Baydin2018].

There's no support for vectorization or GPUs. Performance will be terrible.

See the tests for api usage, and demo.py for a more complex example.

[Baydin2018]Baydin, Atilim Gunes, Barak A. Pearlmutter, Alexey Andreyevich Radul, and Jeffrey Mark Siskind. 2018. “Automatic Differentiation in Machine Learning: A Survey.” Journal of Machine Learning Research 18 (153): 1–43. https://www.jmlr.org/papers/volume18/17-468/17-468.pdf

About

A very small and very slow "deep learning framework." Likely useless for anything other than educational purposes.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages