This project implements reverse mode automatic differentiation with continuation passing style (CPS). Tensors and scalars are both supported with number type of float64, float32, or complex128. Gradient was inspired by Lantern as described by this paper.
-
Notifications
You must be signed in to change notification settings - Fork 0
Reverse Mode Automatic Differentiation with Continuation Passing Style
License
pointlander/gradient
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Reverse Mode Automatic Differentiation with Continuation Passing Style
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published