Thesis Details

Možnosti akcelerace symbolické regrese pomocí kartézského genetického programování

Master's Thesis Student: Hodaň David Academic Year: 2018/2019 Supervisor: Vašíček Zdeněk, doc. Ing., Ph.D.
English title
Acceleration of Symbolic Regression Using Cartesian Genetic Programming
Language
Czech
Abstract

This thesis is focused on finding procedures that would accelerate symbolic regressions in Cartesian Genetic Programming. It describes Cartesian Genetic Programming and its use in the task of symbolic regression. It deals with the SIMD architecture and the SSE and AVX instruction set. Several optimizations that lead to a significant acceleration of evolution in Cartesian Genetic Programming are presented. A method of a bit-level parallel simulation that uses AVX2 vectors allows to process 256 input combinations of a logic circuit in paralell. Similarly it is possible to use a byte-level parallel simulation and work with 32 bytes when evolving an image filter. A new method of batch mutation can accelerate the evolution of combinational logic circuits thousand times depending on the problem size. For example, using a combination of these and other methods the evolution of 5 x 5b multipliers took 5.8 seconds on average on an Intel Core i5-4590 processor.

Keywords

Evolutionary algorithms, cartesian genetic programming, symbolic regression, image filtering, optimization, acceleration, speed

Department
Degree Programme
Information Technology, Field of Study Bioinformatics and Biocomputing
Files
Status
defended, grade A
Date
20 June 2019
Reviewer
Committee
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY FIT BUT), předseda
Grégr Matěj, Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Matoušek Radomil, doc. Ing., Ph.D. (IACS FME BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Citation
HODAŇ, David. Možnosti akcelerace symbolické regrese pomocí kartézského genetického programování. Brno, 2019. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2019-06-20. Supervised by Vašíček Zdeněk. Available from: https://www.fit.vut.cz/study/thesis/22005/
BibTeX
@mastersthesis{FITMT22005,
    author = "David Hoda\v{n}",
    type = "Master's thesis",
    title = "Mo\v{z}nosti akcelerace symbolick\'{e} regrese pomoc\'{i} kart\'{e}zsk\'{e}ho genetick\'{e}ho programov\'{a}n\'{i}",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2019,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/22005/"
}
Back to top