DiffSharp 0.6.2

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There is a newer version of this package available.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 0.6.2
dotnet add package DiffSharp --version 0.6.2
<PackageReference Include="DiffSharp" Version="0.6.2" />
For projects that support PackageReference, copy this XML node into the project file to reference the package.
paket add DiffSharp --version 0.6.2
The NuGet Team does not provide support for this client. Please contact its maintainers for support.

Release Notes

Please visit


for the latest release notes.

NuGet packages (1)

Showing the top 1 NuGet packages that depend on DiffSharp:

Package Downloads
Hype is a proof-of-concept deep learning library, where you can perform optimization on compositional machine learning systems of many components, even when such components themselves internally perform optimization. This is enabled by nested automatic differentiation (AD) giving you access to the automatic exact derivative of any floating-point value in your code with respect to any other. Underlying computations are run by a BLAS/LAPACK backend (OpenBLAS by default).

GitHub repositories

This package is not used by any popular GitHub repositories.

Version History

Version Downloads Last updated
0.8.4-beta 579 8/24/2019
0.8.3-beta 246 7/4/2019
0.8.2-beta 230 6/25/2019
0.8.1-beta 220 6/20/2019
0.8.0-beta 232 6/11/2019
0.7.7 3,024 12/25/2015
0.7.6 619 12/15/2015
0.7.5 610 12/6/2015
0.7.4 667 10/13/2015
0.7.3 585 10/6/2015
0.7.2 572 10/4/2015
0.7.1 568 10/4/2015
0.7.0 574 9/29/2015
0.6.3 1,132 7/18/2015
0.6.2 580 6/6/2015
0.6.1 578 6/2/2015
0.6.0 573 4/26/2015
0.5.10 594 3/27/2015
0.5.9 559 2/26/2015
0.5.8 645 2/23/2015
0.5.7 558 2/17/2015
0.5.6 594 2/13/2015
0.5.5 559 12/15/2014
0.5.4 715 11/23/2014
0.5.3 1,295 11/7/2014
0.5.2 1,285 11/4/2014
0.5.1 572 10/27/2014
0.5.0 598 10/2/2014
Show less