Thesis Details
Mutace v kartézském genetickém programování
This thesis examines various kinds of mutations in the Cartesian Genetic Programming (CGP) on tasks of symbolic regression. The CGP is kind of evolutionary algorithm which operates with executable structures. Programs in CGP are evolved using mutation, which leads to offspring evaluation, which is the most time-consuming part of the algorithm. Finding more suitable kind of mutation can significantly accelerate the creation of new individuals and thus, reduce the time necessary to find a satisfactory solution. This thesis presents four different mutations for CGP. Experiments compare these mutation operators to solve five tasks of symbolic regression. Experiments have shown that a choice of suitable mutation can almost double the computing speed in comparison to the standard mutation.
Symbolic regression, evolutionary algorithm, cartesian genetic programming, mutation.
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Křivka Zbyněk, Ing., Ph.D. (DIFS FIT BUT), člen
Rozman Jaroslav, Ing., Ph.D. (DITS FIT BUT), člen
Strnadel Josef, Ing., Ph.D. (DCSY FIT BUT), člen
@bachelorsthesis{FITBT18120, author = "Ond\v{r}ej Kon\v{c}al", type = "Bachelor's thesis", title = "Mutace v kart\'{e}zsk\'{e}m genetick\'{e}m programov\'{a}n\'{i}", school = "Brno University of Technology, Faculty of Information Technology", year = 2016, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/18120/" }