prikaz prve stranice dokumenta Kombinatorički dizajni za duboko učenje
No public access
master's thesis
Kombinatorički dizajni za duboko učenje
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:997343
Bilić, Ante
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Bilić, A. (2024). Kombinatorički dizajni za duboko učenje (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:997343

Bilić, Ante. "Kombinatorički dizajni za duboko učenje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:997343

Bilić, Ante. "Kombinatorički dizajni za duboko učenje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:997343

Bilić, A. (2024). 'Kombinatorički dizajni za duboko učenje', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 19 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:997343

Bilić A. Kombinatorički dizajni za duboko učenje [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 19] Available at: https://urn.nsk.hr/urn:nbn:hr:168:997343

A. Bilić, "Kombinatorički dizajni za duboko učenje", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:997343

Metadata
TitleKombinatorički dizajni za duboko učenje
Title (english)Combinatorial designs for deep learning
AuthorAnte Bilić
MentorMario Osvin Pavčević (mentor)
Committee memberMario Osvin Pavčević (predsjednik povjerenstva)
Committee memberDomagoj Kovačević (član povjerenstva)
Committee memberMate Puljiz (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-07-09, Croatia
Abstract
U sklopu ovog diplomskog rada razvijena su dva načina generiranja dropout dizajna. Prvi način je generiranje dropout dizajna genetskim algoritmom, dok je drugi način trivijalno generiranje određenog tipa dropout dizajna. Generirani dropout dizajni su se koristili prilikom treniranja potpuno povezanih konvolucijskih i povratnih neuronskih mreža uz pomoć izrađene implementacije za primjenu generiranih dizajna. Dobiveni rezultati kombinatoričkog dropouta na različitim mrežama su uspoređeni sa stohastičkim dropoutom i normalizacijom nad grupom. Korištenjem statističkih testova uspoređeni su rezultati i dobiveni zaključci.
Abstract (english)
Within this master ́s thesis, two different ways of generating dropout designs have been developed. The first one is generating dropout designs by genetic algorithm, while the other one is the trivial generating of a specific type of dropout designs. The generated dropout designs were used during the training process of feedforward, convolutional and recurrent neural networks, assisted by custom implementation for using generated designs. The received results of combinatorial dropout on different networks have been compared to stochastic dropout and batch normalization. By using statistical tests, the results have been compared and the conclusions have been made.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:997343
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 20:06:33