Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://diffsharp.github.io/DiffSharp/
DiffSharp: Differentiable Functional Programming
https://diffsharp.github.io/DiffSharp/
autodiff deep-learning dotnet gpu machine-learning neural-network tensor
Last synced: 24 days ago
JSON representation
DiffSharp: Differentiable Functional Programming
- Host: GitHub
- URL: https://diffsharp.github.io/DiffSharp/
- Owner: DiffSharp
- License: bsd-2-clause
- Created: 2014-08-28T16:19:45.000Z (almost 10 years ago)
- Default Branch: dev
- Last Pushed: 2024-04-15T20:25:41.000Z (about 2 months ago)
- Last Synced: 2024-05-06T23:40:34.076Z (29 days ago)
- Topics: autodiff, deep-learning, dotnet, gpu, machine-learning, neural-network, tensor
- Language: F#
- Homepage: http://diffsharp.github.io
- Size: 162 MB
- Stars: 574
- Watchers: 40
- Forks: 67
- Open Issues: 37
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- AI - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / [Tools](#tools-1))
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / [Tools](#tools-1))
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET)
- awesome-dotnet-datascience - DiffSharp - DiffSharp allows for exact and efficient calculation of derivatives, by systematically invoking the chain rule of calculus at the elementary operator level during program execution. (Machine Learning and Differential Programming)
- awesome-machine-learnings - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / [Tools](#tools-1))
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / [Tools](#tools-1))
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / [Tools](#tools-1))
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / Tools)
- awesome-machine-learning - DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. 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, for applications such as hyperparameter optimization. (.NET / Tools)
README
-----------------------------------------
[](https://github.com/DiffSharp/DiffSharp/actions)
[](https://coveralls.io/github/DiffSharp/DiffSharp?branch=)
This is the development branch of DiffSharp 1.0.
> **NOTE: This branch is undergoing development. It has incomplete code, functionality, and design that are likely to change without notice; when using TorchSharp backend, only x64 platform is currently supported out of the box, see [DEVGUIDE.md] for more details.**
DiffSharp is a tensor library with support for [differentiable programming](https://en.wikipedia.org/wiki/Differentiable_programming). It is designed for use in machine learning, probabilistic programming, optimization and other domains.
**Key features**
* Nested and mixed-mode differentiation
* Common optimizers, model elements, differentiable probability distributions
* F# for robust functional programming
* PyTorch familiar naming and idioms, efficient LibTorch CUDA/C++ tensors with GPU support
* Linux, macOS, Windows supported
* Use interactive notebooks in Jupyter and Visual Studio Code
* 100% open source
## Documentation
You can find the documentation [here](https://diffsharp.github.io/), including information on installation and getting started.
Release notes can be found [here](https://github.com/DiffSharp/DiffSharp/blob/dev/RELEASE_NOTES.md).
## Communication
Please use [GitHub issues](https://github.com/DiffSharp/DiffSharp/issues) to share bug reports, feature requests, installation issues, suggestions etc.
## Contributing
We welcome all contributions.
* Bug fixes: if you encounter a bug, please open an [issue](https://github.com/DiffSharp/DiffSharp/issues) describing the bug. If you are planning to contribute a bug fix, please feel free to do so in a pull request.
* New features: if you plan to contribute new features, please first open an [issue](https://github.com/DiffSharp/DiffSharp/issues) to discuss the feature before creating a pull request.
## The Team
DiffSharp is developed by [Atılım Güneş Baydin](http://www.robots.ox.ac.uk/~gunes/), [Don Syme](https://www.microsoft.com/en-us/research/people/dsyme/) and other contributors, having started as a project supervised by the automatic differentiation wizards [Barak Pearlmutter](https://scholar.google.com/citations?user=AxFrw0sAAAAJ&hl=en) and [Jeffrey Siskind](https://scholar.google.com/citations?user=CgSBtPYAAAAJ&hl=en).
## License
DiffSharp is licensed under the BSD 2-Clause "Simplified" License, which you can find in the [LICENSE](https://github.com/DiffSharp/DiffSharp/blob/dev/LICENSE) file in this repository.