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

DiffSharp


Summary:
DiffSharp is an automatic differentiation (AD) library implemented in the F# language. It supports C# and the other common language infrastructure languages. The library is under active development by Atılım GŁneş Baydin and Barak A. Pearlmutter mainly for research applications in machine learning, as part of their work at the Brain and Computation Lab, Hamilton Institute, National University of Ireland Maynooth.

Please visit the project website for detailed documentation and usage examples.

URL: http://diffsharp.github.io/DiffSharp/

Developers:
  • Atilim Gunes Baydin
  • Barak A. Pearlmutter

Mode: Forward
Reverse
 
Method: Operator overloading
 
Supported Language: .NET
C#
F#

Reference:
A. G. Baydin, B. A. Pearlmutter, A. A. Radul, J. M. Siskind
Automatic differentiation in machine learning: a survey
Article in arXiv preprint arXiv:1502.05767, 2015



Supported Platforms:
  • Windows
  • Unix/Linux
  • Mac


Licensing: open source

References on DiffSharp in our publication database:  3

10+
#Pubs
0
2
1
'15 '16
Year

Related Research Groups:

  

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