Shark Documentation

Scope

SHARK is a modular C++ library for the design and optimization of adaptive systems. It provides methods for linear and nonlinear optimization, in particular evolutionary and gradient-based algorithms, kernel-based learning algorithms and neural networks, and various other machine learning techniques. SHARK serves as a toolbox to support real world applications as well as research in different domains of computational intelligence. The libraries are not necessarily dependent on any third party software. The sources are compatible with the following platforms: Windows, Solaris, MacOS X, and Linux.

Resources

	Tutorials
	Frequently Asked Questions (FAQ)

Main Library Documentation

	ReClaM This library serves as a toolbox for Regression and Classification Methods. It provides different models for regression and classification, in particular kernel-based algorithms (e.g., SVMs, Gaussian Processes) and neural networks. For the adaptation of model parameters, ReClaM offers several gradient-based algorithms. To achieve high flexibility, ReClaM has a modular structure, in which model, error functional, and optimizer can freely be combined.
	EALib The EALib is a library providing Evolutionary Algorithms (in particular evolution strategies and genetic algorithms) and related techniques.
	MOO-EALib The MOO-EALib extends the EALib by providing various evolutionary Multi-Objective Optimization algorithms.

Tools Documentation

	Mixture Library for the representation and optimization of mixture density models.
	Array A convenient array/matrix library.
	Rng A system independent random number generator with support for lots of common discrete and continuous distributions.
	LinAlg This library provides basic methods from linear algebra for matrix inversion, SVD, etc.
	FileUtil Convenient file input/output and support for configuration files.

Paper Describing the Library

@Article{shark08,
  author = {Christian Igel and Tobias Glasmachers and Verena Heidrich-Meisner},
  title = {Shark},
  journal = {Journal of Machine Learning Research},
  year = {2008},
  volume = {9},
  pages = {993-996},
}