GEATbx.com

Evolutionary Algorithms for MATLAB
(incl. Genetic Algorithms and Genetic Programming)

Evolutionary Algorithms are the common term used for algorithms based on principles of nature (evolution, genetic). Evolutionary Algorithms contain genetic algorithms, evolution strategies, evolutionary programming and genetic programming.

GEATbx: Genetic and Evolutionary Algorithm Toolbox for use with Matlab

• Hartmut Pohlheim
• 1994 (v. 1.7) / July 1997 (v. 1.92) / November 1998 (v. 1.95) / July 2001 (v. 3.3) / June 2004 (v. 3.5) / November 2005 (v. 3.7) [regularly updated]
• Features and Implementation of GEATbx
• Documentation of the GEATbx
• Introduction into Evolutionary Algorithms: Principles, Methods and Algorithms; structure, operators and research results; can be used as introduction or as reference

GADS: Genetic Algorithm and Direct Search Toolbox for use with MATLAB

• The MathWorks, Inc., USA
• April 2004 (v. 1.0.1), September 2005 (v. 2.0)
• Product description of the GADS
• Key Features:
  • genetic algorithms and direct search algorithms in one toolbox
  • integration of optimization toolbox (the GADS extends the optimization toolbox)
  • graphical user interface, command-line options
  • visualization of the optimization process and results
• good implementation of real-valued and binary representation of genetic algorithms, very good visualization
• (v. 2.0) inclusion of constraint handling techniques

Genetic Algorithm Toolbox for use with MATLAB

• Andrew Chipperfield, Peter Fleming, Hartmut Pohlheim and Carlos Fonseca; University of Sheffield, UK
• April 1994 (v. 1.2)
• A. J. Chipperfield, P. J. Fleming, H. Pohlheim and C. M. Fonseca, "Genetic Algorithm Toolbox User's Guide", ACSE Research Report No. 512, University of Sheffield, 1994.
• Manual of the GATbx (pdf, 94 pages)
• Key Features:
  • Support for binary, integer and real-valued representations.
  • A wide range of genetic operators.
  • High-level entry points to most low-level functions.
  • Many variations on the standard GA.
  • Support for virtual multiple subpopulations.
• This toolbox is freely available from the above website. It is still a good start into the work with Evolutionary Algorithms in Matlab (even when more than 10 years old).
• Evolutionary Computation Research Group (University of Sheffield, UK, Automatic Control and Systems Engineering)

CMA Evolution Strategy for Noisy and Global Optimization: Implementations in MATLAB

• Nikolaus Hansen
• 2003 (v. 2)
• best implementation of the CMA (Evolution Strategy with Covariance Matrix Adaptation) in Matlab available

GPLAB - a Genetic Programming toolbox for MATLAB

• Sara Silva
• 2004 (v. 2)
• Features of GPLAB
• Manual of GPLAB (pdf)

Genetic Algorithm Optimization Toolbox (GAOT)

• Chris Houck, Jeff Joines and Mike Kay; North Carolina State University, USA
• April 1996 (v. 5)
• GAOT implements simulated evolution in the Matlab environment using both binary and real representations. This implementation is very flexible in the genetic operators, selection functions, termination functions as well as the evaluation functions that can be used.
• Houck, C., Joines, J., and Kay, M., " A Genetic Algorithm for Function Optimization: A Matlab Implementation", NCSU-IE TR 95-09, 1995.

FlexTool (GA) - Genetic Algorithm Toolbox for Matlab Users

• CynapSys, LLC, USA (was Flexible Intelligence Group, LLC)
• 1996, there seem to be no updates, no longer available (2006-09)
• commercial, quite expensive

Genetic Programming with Matlab

• What used to be the Symbolic Optimisation Research Group (SORG) at the University of Newcastle upon Tyne no longer exists.
  The code is not available. There were plans for a new version (2001/06, Dominic Searson, Advanced Process Control Group). But nothing available at the moment.

Other pages providing an overview of Evolutionary / Genetic Algorithms (EA) tools in Matlab

• Mathtools.net provides information on many scientific applications, including on MATLAB/Genetic_algorithms