prikaz prve stranice dokumenta Analiza utjecaja odabira hiperparametara na kolaborativno učenje
No public access
master's thesis
Analiza utjecaja odabira hiperparametara na kolaborativno učenje
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:102235
Pikelj, Ivan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pikelj, I. (2020). Analiza utjecaja odabira hiperparametara na kolaborativno učenje (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:102235

Pikelj, Ivan. "Analiza utjecaja odabira hiperparametara na kolaborativno učenje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:102235

Pikelj, Ivan. "Analiza utjecaja odabira hiperparametara na kolaborativno učenje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:102235

Pikelj, I. (2020). 'Analiza utjecaja odabira hiperparametara na kolaborativno učenje', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 28 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:102235

Pikelj I. Analiza utjecaja odabira hiperparametara na kolaborativno učenje [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 July 28] Available at: https://urn.nsk.hr/urn:nbn:hr:168:102235

I. Pikelj, "Analiza utjecaja odabira hiperparametara na kolaborativno učenje", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:102235

Metadata
TitleAnaliza utjecaja odabira hiperparametara na kolaborativno učenje
Title (english)Analyzing the Influence of Hyperparameters on Federated Learning
AuthorIvan Pikelj
MentorDamir Pintar (mentor)
Committee memberDamir Pintar (predsjednik povjerenstva)
Committee memberLuka Humski (član povjerenstva)
Committee memberBoris Vrdoljak (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Kolaborativno učenje je novi pristup treniranju modela umjetne inteligencije na distribuiranim podacima i uređajima. Ovakvim pristupom podaci ostaju pohranjeni lokalno i time se čuva privatnost. Treniranje modela u tako heterogenom sustavu dovodi do novih izazova različitih od već dobro utvrđenih metoda. U radu su opisane uobičajene metode kolaborativnog procesa, a dokaz koncepta ukazuje na utjecaj hiperparametara na proces. Dokaz koncepta pokazuje izazove koji se mogu pojaviti u procesu treniranja nad akademskim podacima kategorizacije MNIST brojeva i kako ih se može ublažiti dobrim odabirom hiperparametara, ovisno o problemu.
Abstract (english)
Federated learning is a new approach to train models of artificial intelligence on distributed data and devices. With this approach data can be left stored locally and will preserve privacy. Training models in such elaborate system induces new challenges in contrast to well established methods. Paper describes common methods to achieve such process as well gives proof of concept to demonstrate significance of hyperparameters on the process. Proof of concept demonstrates challenges models might occur in process of training on academic data of categorizing MNIST numbers and how it can be alleviated via good hyperparameter selection depending on problem.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:102235
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 on2023-01-13 10:36:31