Optimiranje evolucijskim algoritmima

Kuzmić, Jurica (2017) Optimiranje evolucijskim algoritmima. = Optimization with evolutionary algorithms. Undergraduate thesis , Sveučilište u Zagrebu, Fakultet strojarstva i brodogradnje, UNSPECIFIED. Mentor: Lisjak, Dragutin.

[img]
Preview
Text
Kuzmić_2017_zavrsni_preddiplomski.pdf - Published Version Jezik dokumenta:Croatian

Download (3MB) | Preview
[img] Text
Kuzmić_Jurica_autorska_izjava_zavrsni_2017.pdf - Published Version
Restricted to Repository staff only Jezik dokumenta:Croatian

Download (481kB)

Abstract (Croatian)

Ovaj rad bavi se pružanjem teorijskog uvoda o radu evolucijskih algoritama (EA) kao algoritama koji se mogu upotrijebiti za optimizaciju brojnih problema iz inženjerske struke. Područje istraživanja EA-ma nastaje unutar područja strojnog učenja kojem je cilj osposobljavanje računala za samostalno programiranje. Inspiraciju u svojem radu, EA-mi posuđuju od biološke evolucije prema teoriji Charlesa Darwina. Osnovnim skupinama EA-ma smatraju se: evolucijske strategije (ES), evolucijsko programiranje (EP), genetski algoritmi (GA) te genetsko programiranje (GP). Iznesena teorija o radu algoritama može se upotrijebiti za rješavanje vrlo velikog broja problema kod kojih je moguća primjena nekih od spomenutih algoritama, a upotreba navedene teorije demonstrirana je na primjerima rada GA i GP algoritma koji su dani na završetku ovoga rada.

Abstract

This thesis provides theoretical introduction of the way in which evolutionary algorithms (EAs) work and can be used regarding optimization of wide number of problems that engineers face. EA field of study has formed as part of machine learning, whose main goal is creating computers capable of self-programming. EAs borrow inspiration from biological evolution, which is a theory brought forward by Charles Darwin. Main members of EAs are: evolutionary strategies (ES), evolutionary programming (EP), genetic algorithms (GA) and genetic programming (GP). Theory about the way EAs work that is presented here, can be applied to very large number of problems and is also used on examples of GA and GP runs, given at the end of this thesis.

Item Type: Thesis (Undergraduate thesis)
Uncontrolled Keywords: evolucijski algoritmi, evolucijske strategije, evolucijsko programiranje, genetski algoritmi, genetsko programiranje, metode prikaza rješenja, metode selekcije, varijacijski operatori, regresijska analiza genetskim programiranjem (GP)
Keywords (Croatian): evolutionary algorithms (EAs), evolutionary strategies (ES), evolutionary programming (EP), genetic algorithms (GA), genetic programming (GP), solution representation, selection methods, variation operator, regression analysis using genetic programming (GP)
Subjects: TECHNICAL SCIENCE > Mechanical Engineering
Divisions: 700 Department of Industrial Engineering > 720 Chair of Production Control
Date Deposited: 25 Sep 2017 09:01
Last Modified: 10 Oct 2017 14:35
URI: http://repozitorij.fsb.hr/id/eprint/7993

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

Nema podataka za dohvacanje citata