AD Tool: AutoDiff_Library
Introduction
Applications
Tools
Research Groups
Workshops
Publications
My Account
About

AutoDiff_Library


Summary:
This standalone AD library builds the computational graph and performs reverse gradient as well as reverse Hessian and Hessian-vector product algorithms on the graph. It is currently used in the parallel implementation of the Structured Modelling Language (http://www.maths.ed.ac.uk/ERGO/sml).

URL: https://github.com/fqiang/autodiff_library

Developers:
Mode: Forward
Reverse
 
Supported Language: C/C++

Features:
1. Very easy access and light weight C++/C library
2. Build computation graph as a DAG.
3. Provide reverse gradient and reverse Hessian-vector product.
4. Implemented the full reverse Hessian algorithm: edge_push (by Robert Gower) and pattern detection algorithm.
5. Contemporary Object-Oriented Implementation in C++.
6. Implement Unit-test using Boost Test Framework.

More detail can be find on the project wiki page at:
https://github.com/fqiang/autodiff_library/wiki

Supported Platforms:
  • Unix/Linux


Licensing: open source

Entries in our publication database that actually use AutoDiff_Library in the numerical experiments:  0

The following diagram shows these entries versus the year of the publication.

10+
#Entries
0
Year
  

Contact:
autodiff.org
Username:
Password:
(lost password)