prikaz prve stranice dokumenta Usporedba metoda za učenje neuronskih mreža za igru zmija
No public access
undergraduate thesis
Usporedba metoda za učenje neuronskih mreža za igru zmija
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:682469
Goršić, Leo
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Goršić, L. (2022). Usporedba metoda za učenje neuronskih mreža za igru zmija (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:682469

Goršić, Leo. "Usporedba metoda za učenje neuronskih mreža za igru zmija." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:682469

Goršić, Leo. "Usporedba metoda za učenje neuronskih mreža za igru zmija." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:682469

Goršić, L. (2022). 'Usporedba metoda za učenje neuronskih mreža za igru zmija', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:682469

Goršić L. Usporedba metoda za učenje neuronskih mreža za igru zmija [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:682469

L. Goršić, "Usporedba metoda za učenje neuronskih mreža za igru zmija", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:682469

Metadata
TitleUsporedba metoda za učenje neuronskih mreža za igru zmija
Title (english)Comparison of learning methods of neural networks for the snake game
AuthorLeo Goršić
MentorMarko Đurasević (mentor)
Committee memberMarko Đurasević (predsjednik povjerenstva)
Committee memberNikolina Frid (član povjerenstva)
Committee memberEda Jovičić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Igra „Zmija“ jednostavna je igra pogodna za implementaciju agenta koji bi putem umjetne neuronske mreže igrao igru. Obzirom kako ne postoji općenita formula za izbor optimalnih parametara umjetnih neuronskih mreža potrebno je metodom isprobavanja pronaći optimalne parametre. U radu predstavljena je metodika isprobavanja i vrednovanja različitih varijanti neuronskih mreža. Sve varijante neuronskih mreža su testirane te su rezultati prikazani box plot dijagramima. Na kraju je dana kratka diskusija i moguća objašnjenja rezultata.
Abstract (english)
The game "Snake" is a simple game suitable for the implementation of an agent who would play the game with help form artificial neural network. Since there is no general formula for selecting the optimal parameters of artificial neural networks, it is necessary to them by testing. This paper presents a methodology for testing and evaluating different variants of neural networks. All neural network variants were tested and the results are shown in box plot diagrams. At the end, a short discussion and possible explanations of the results are given.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:682469
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-15 10:13:26