https://github.com/pointlander/gradient

Reverse Mode Automatic Differentiation with Continuation Passing Style
https://github.com/pointlander/gradient

gradient machine-learning

Last synced: 5 months ago
JSON representation

Reverse Mode Automatic Differentiation with Continuation Passing Style

• Host: GitHub
• URL: https://github.com/pointlander/gradient
• Owner: pointlander
• License: bsd-3-clause
• Created: 2019-07-13T03:10:31.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2026-01-30T17:51:31.000Z (5 months ago)
• Last Synced: 2026-01-31T09:40:15.732Z (5 months ago)
• Topics: gradient, machine-learning
• Language: Go
• Homepage:
• Size: 366 KB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
[![godoc](https://godoc.org/github.com/pointlander/gradient?status.svg)](https://godoc.org/github.com/pointlander/gradient)

# Reverse Mode Automatic Differentiation with Continuation Passing Style

This project implements [reverse mode automatic differentiation](https://en.wikipedia.org/wiki/Automatic_differentiation) with [continuation passing style](https://en.wikipedia.org/wiki/Continuation-passing_style) (CPS). Tensors and scalars are both supported with number type of float64, float32, or complex128. Gradient was inspired by [Lantern](https://feiwang3311.github.io/Lantern/) as described by this [paper](http://papers.nips.cc/paper/8221-backpropagation-with-callbacks-foundations-for-efficient-and-expressive-differentiable-programming.pdf).