prikaz prve stranice dokumenta Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara
  Download
PDF 3.72 MB
master's thesis
Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:235:133232
Homolak, Sandi
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Institutional repository: Repository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb

Cite this document

Homolak, S. (2022). Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara (Master's thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:133232

Homolak, Sandi. "Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:235:133232

Homolak, Sandi. "Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:235:133232

Homolak, S. (2022). 'Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara', Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 13 July 2024, https://urn.nsk.hr/urn:nbn:hr:235:133232

Homolak S. Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara [Master's thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2022 [cited 2024 July 13] Available at: https://urn.nsk.hr/urn:nbn:hr:235:133232

S. Homolak, "Duboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara", Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:235:133232

Metadata
TitleDuboki evolucijski algoritmi za samopodešavanje evolucijskih hiperparametara
Title (english)Deep evolutionary algorithms for evolutionary parameters self-tuning
AuthorSandi Homolak
MentorPetar Ćurković (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2022-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom diplomskom radu predlaže se metoda dubokog evolucijskog algoritma temeljena na ugnježđivanju dvaju evolucijskih algoritama s ciljem pronalaska kvalitetne kombinacije hiperparametara algoritama za različite optimizacijske probleme. Dan je pregled područja evolucijskog računarstva s naglaskom na evolucijske algoritme. Opisana je struktura evolucijskih algoritama te raznih metoda koje se koriste za postavljanje njihovih hiperparametara. U nastavku rada slijedi strukturni prikaz metode koja se predlaže te konačno, njezina implementacija na nekoliko standardnih ispitnih zadataka.
Abstract (english)
In this thesis, a deep evolutionary algorithm method based on the nesting of two evolutionary algorithms is proposed with the aim of finding a set of high-quality hyperparameters for different optimization problems. An overview of the field of evolutionary computation with an emphasis on evolution algorithms is given. The structure of evolutionary algorithms and various hyperparameter tuning methods are described. Furthermore, a structural presentation of the purposed method is shown, and finally, its implementation on several benchmark problems.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:133232
Study programmeTitle: Mechanical Engineering; specializations in: Design, Process and Energy Engineering, Production Engineering, Engineering Modelling and Computer Simulation, Marine Engineering, Industrial Engineering and Management, Materials Engineering, Mechatronics and Robotics, Autonomous Systems
Course: Mechatronics and Robotics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-11-29 10:03:03