Shark machine learning library

http://image.diku.dk/shark/sphinx_pages/build/html/index.html

Summary¶

Note

This is Shark 3.0 beta. See the news for more information.

SHARK is a fast, modular, feature-rich open-source C++ machine learning library.It provides methods for linear and nonlinear optimization, kernel-based learningalgorithms, neural networks, and various other machine learning techniques (see thefeature list below).It serves as a powerful toolbox for real world applications as well as research.Shark depends on Boost and CMake.It is compatible with Windows, Solaris, MacOS X, and Linux. Shark is licensed underGPLv3.

For an overview over the previous major release of Shark (2.0) werefer to:

Christian Igel, Verena Heidrich-Meisner, and Tobias Glasmachers. Shark.Journal of Machine Learning Research 9, pp. 993-996, 2008.[ Bibtex]

Where to start¶

In the menu above, click on “Getting started”, or use this direct link to theinstallation instructions.After installation, there is a guide to the different documentation pages availablehere.

Why Shark?¶

Speed and flexibility

Shark provides an excellent trade-off between flexibility andease-of-use on the one hand, and computational efficiency on the other.

One for all

Shark offers numerous algorithms from various machine learning andcomputational intelligence domains in a way that they can be easilycombined and extended.

Unique features

Shark comes with a lot of powerful algorithms that are to our bestknowledge not implemented in any other library, for example in thedomains of model selection and training of binary and multi-class SVMs,or evolutionary single- and multi-objective optimization.

Selected features¶

Shark currently supports:

• Supervised learning
  • Linear discriminant analysis (LDA), Fisher–LDA
  • Naive Bayes classifier (supporting generic distributions)
  • Linear regression
  • Support vector machines (SVMs) for one-class, binary and truemulti-category classification as well as regression; includes fast variants for linear kernels.
  • Feed-forward and recurrent multi-layer artificial neural networks
  • Radial basis function networks
  • Regularization networks as well as Gaussian processes for regression
  • Iterative nearest neighbor classification and regression
  • Decision trees and random forests
• Unsupervised learning
  • Principal component analysis
  • Restricted Boltzmann machines (including many state-of-the-artlearning algorithms)
  • Hierarchical clustering
  • Data structures for efficient distance-based clustering
• Evolutionary algorithms
  • Single-objective optimization (e.g., CMA–ES)
  • Multi-objective optimization (in particular, highly efficientalgorithms for computing as well as approximating the contributing hypervolume)
• Fuzzy systems
• Basic linear algebra and optimization algorithms