Article

Article title APPLICATION OF GENETIC PROGRAMMING FOR DECISION OF SIMBOLIC REGRESSION PROBLEM
Authors M.V. Lisyak
Section SECTION I. EVOLUTIONARY MODELLING, GENETIC AND BIONIC ALGORITHMS
Month, Year 07, 2010 @en
Index UDC 658.512.2.011.5
DOI
Abstract There is considered the decision of symbolic regression problem by means of genetic programming method. The problem input data include the set of independent variables and constants (arguments of function), the set of elementary functions, list of fitness-cases (table containing reference values of unknown function at different values of the arguments). Result of the problem decision is mathematical expression in symbolic form, which fits the functional dependence, described by fitness-cases, in the best way. There are described the problem and the method of decision, the way of alternative decisions representation and quality measuring, algorithm of genetic search, modifications of standard genetic operators, parameters of search algorithm. The result of running a program, which realizes described method, is considered.

Download PDF

Keywords Genetic programming; genetic algorithm; symbolic regression; fitness measures; reproduction; crossover; over-selection.
References 1. John Koza. Genetically Breeding Populations of Computer Programs to Solve Problems of Artificial Intelligence. Proceedings of the Second International Conference on Tools for AI. Herndon, Virginia, November 6-9, 1990. Los Alamitos, CA: IEEE Computer Society Press. – P. 819-827.
2. John Koza. Integrating Symbolic Processing into Genetic Algorithms. Workshop on Integrating Symbolic and Neural Processes at AAAI-90 in Boston. July 29, 1990.
3. John Koza. Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA: The MIT Press, 1992. – 840 p.
4. Zelinka Ivan. Symbolic regression – an overview. http://www.mafy.lut.fi/EcmiNL/ older/ecmi35/node70.html.
5. Ricardo Poli, William B. Langdon, Nicolas F. McPhee. A field guide to Genetic programming. http://www.gp-field-guide.org.uk. 2008. – 250 p.
6. Курейчик В.М., Родзин С.И. Эволюционные алгоритмы: генетическое программирование // Известия академии наук. Теория и системы управления. – 2002. – № 1.

Comments are closed.