- author = "Michaela Drahosova",
- title = "Coevolution of Fitness Predictors in Cartesian Genetic Programming",
- title2 = "Koevoluce prediktoru fitness v kartezskem genetickem programovani",
- school = "Brno University of Technology, Czech Republic",
- year = "2017",
- keywords = "genetic algorithms, genetic programming, cartesian genetic programming, Evolutionary design, coevolutionary algorithms, fitness prediction",
-
URL = "
http://hdl.handle.net/11012/187309",
-
URL = "
https://dspace.vutbr.cz/xmlui/bitstream/handle/11012/187309/thesis-1.pdf",
- timestamp = "Tue, 09 Jun 2020 01:00:00 +0200",
-
biburl = "https://dblp.org/rec/phd/basesearch/Drahosova17.bib",
- bibsource = "dblp computer science bibliography, https://dblp.org",
- size = "109 pages",
- abstract = "Cartesian genetic programming (CGP) is an evolutionary based machine learning method which can automatically design computer programs or digital circuits. CGP has been successfully applied in a number of challenging real-world problem domains. However, the computational power that the design based on CGP needs for obtaining innovative results is enormous for most applications. In CGP, every candidate program is executed to determine a fitness value, representing the degree to which it solves the problem. Typically, the most time consuming part of CGP is the fitness evaluation. This thesis proposes to introduce coevolution of fitness predictors to CGP in order to accelerate the evolutionary design performed by CGP. Fitness predictors are small subsets of the training data, which are used to estimate candidate program fitness instead of performing an expensive objective fitness evaluation. Coevolution of fitness predictors is an optimization method of the fitness modeling that reduces the fitness evaluation cost and frequency, while maintaining the evolutionary process. In this thesis, the coevolutionary algorithm is adapted for CGP and three approaches to fitness predictor encoding are introduced and examined. The proposed approach is evaluated using five symbolic regression benchmarks and in the image filter design problem. The method enabled us to significantly reduce the time of evolutionary design for considered class of problems.",
-
notes = "In english.
Supervisor: Lukas Sekanina",
