GP Kernel The GP kernel is a C++ class library that can be used to apply genetic programming techniques to all kinds of problems. An integral component is the ability to produce automatically defined functions as found in Koza's "Genetic Programming II". Technical documentation (postscript format) is included. There is also a short introduction into genetic programming. Features: Automatically defined functions (ADFs). Tournament and fitness proportionate selection. Demetic grouping. Optional steady state genetic programming kernel. Steady state means that not a complete new population is built up every generation, but bad performing GPs are replaced by newly evolved ones. This uses approximately half the memory! Subtree crossover. Swap and shrink mutation. A way of changing every parameter of the system without recompilation. Capacity for multiple populations (if you have the resources). Loading and saving of populations and genetic programs. Standard random number generator for complete portability. This has been improved: population sizes of over 250000 are possible now. Explanations of how to write the modules for evolving code. Examples. A parameter study about the influence of every important parameter. Completely ANSI C++ compliant. Full and wonderful comments dispersed throughout the code. Internal parameter checks (can be turned off by a compiler switch): The kernel complains if the programmer makes a mistake.

Current Version:   0.5.2 License Type:   GPL

Home Site: http://www.emk.e-technik.tu-darmstadt.de/~thomasw/gp.html Source Code Availability:   Yes (full C++ sources) Available Binary Packages: Debian Package:   No RedHat RPM Package:   No Other Packages:   No Targeted Platforms: C++, tested with GNU C++ Compiler 2.7.0 and C++ Compiler by SUNSoft Software/Hardware Requirements: Lot's of RAM and a fast computer for big and difficult problems.

Other Links: http://www-cs-faculty.stanford.edu/~koza (John Koza's Home Page) http://www.salford.ac.uk/eee/genetic.html (Adam Fraser's Home Page) http://www.aic.nrl.navy.mil/galist/src (GA Archive Source Code Collection) Mailing Lists/USENET News Groups: comp.ai.genetic (Genetic Programming) User Comments: Documentation format other than postscript needed (for the operation systems written by Microsoft, ugh ...). The author is working on it, but he doesn't know when the documentation will be released in HTML format. See A Screen Shot? (Not Yet)

  SAL Home   |   Other Scientific Fields   |   Artificial Intelligence