https://github.com/invenia/nabla.jl

A operator overloading, tape-based, reverse-mode AD
https://github.com/invenia/nabla.jl

autodiff automatic-differentiation julia julia-language

Last synced: 3 days ago
JSON representation

A operator overloading, tape-based, reverse-mode AD

• Host: GitHub
• URL: https://github.com/invenia/nabla.jl
• Owner: invenia
• License: other
• Archived: true
• Created: 2017-03-23T15:44:42.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2023-04-18T02:16:05.000Z (over 1 year ago)
• Last Synced: 2024-09-30T15:18:31.301Z (3 days ago)
• Topics: autodiff, automatic-differentiation, julia, julia-language
• Language: Julia
• Homepage:
• Size: 1.4 MB
• Stars: 67
• Watchers: 15
• Forks: 5
• Open Issues: 40
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Nabla

[![CI](https://github.com/Invenia/Nabla.jl/workflows/CI/badge.svg)](https://github.com/Invenia/Nabla.jl/actions?query=workflow%3ACI)

[![codecov.io](https://codecov.io/github/invenia/Nabla.jl/coverage.svg?branch=master)](https://codecov.io/github/invenia/Nabla.jl?branch=master)

[![Stable Docs](https://img.shields.io/badge/docs-stable-blue.svg)](https://invenia.github.io/Nabla.jl/stable)

[![Latest Docs](https://img.shields.io/badge/docs-latest-blue.svg)](https://invenia.github.io/Nabla.jl/latest)

# No Longer Maintained

This project is no longer actively maintained, as it has been thoroughly superceeded by other AD projects in the Julia ecosystem.

# README

Nabla.jl is a reverse-mode automatic differentiation package targetting machine learning use cases.

As such, we have (for example) prioritised support for linear algebra optimisations and higher-order functions over the ability to take higher-order derivatives (Nabla currently only supports first-order derivatives).

The [latest docs](https://invenia.github.io/Nabla.jl/latest/), and code in the [examples](examples) folder, best indicate how to use the package.

Given the early stage of development, we anticipate a number of bugs and performance issues.

If you encounter any of these or have any particular feature requests, please raise an issue and let us know.