DiffSharp 0.6.1

DiffSharp is an automatic differentiation (AD) library implemented in the F# language. It supports C# and the other CLI languages.

AD allows exact and efficient calculation of derivatives, by systematically invoking the chain rule of calculus at the elementary operator level during program execution. AD is different from numerical differentiation, which is prone to truncation and round-off errors, and symbolic differentiation, which suffers from expression swell and cannot handle algorithmic control flow.

Using the DiffSharp library, derivative calculations (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) can be incorporated with minimal change into existing algorithms. Operations can be nested to any level, meaning that you can compute exact higher-order derivatives and differentiate functions that are internally making use of differentiation. Please see the API Overview page for a list of available operations.

The library is under active development by Atılım Güneş 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.

There is a newer version of this package available.
See the version list below for details.
Install-Package DiffSharp -Version 0.6.1
dotnet add package DiffSharp --version 0.6.1
<PackageReference Include="DiffSharp" Version="0.6.1" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add DiffSharp --version 0.6.1
The NuGet Team does not provide support for this client. Please contact its maintainers for support.

Release Notes

Please visit

https://github.com/gbaydin/DiffSharp/releases

for the latest release notes.

This package is not used by any popular GitHub repositories.

Version History

Version Downloads Last updated
0.8.4-beta 258 8/24/2019
0.8.3-beta 157 7/4/2019
0.8.2-beta 152 6/25/2019
0.8.1-beta 144 6/20/2019
0.8.0-beta 162 6/11/2019
0.7.7 2,685 12/25/2015
0.7.6 498 12/15/2015
0.7.5 492 12/6/2015
0.7.4 538 10/13/2015
0.7.3 465 10/6/2015
0.7.2 462 10/4/2015
0.7.1 462 10/4/2015
0.7.0 466 9/29/2015
0.6.3 997 7/18/2015
0.6.2 485 6/6/2015
0.6.1 472 6/2/2015
0.6.0 461 4/26/2015
0.5.10 491 3/27/2015
0.5.9 466 2/26/2015
0.5.8 536 2/23/2015
0.5.7 449 2/17/2015
0.5.6 486 2/13/2015
0.5.5 469 12/15/2014
0.5.4 618 11/23/2014
0.5.3 1,150 11/7/2014
0.5.2 1,167 11/4/2014
0.5.1 471 10/27/2014
0.5.0 498 10/2/2014
Show less