prikaz prve stranice dokumenta Generativni modeli u dubokom strojnom učenju
Access restricted to students and staff of home institution
master's thesis
Generativni modeli u dubokom strojnom učenju
2020. urn:nbn:hr:166:383381
Ćorić, Mate
University of Split
Faculty of Science
Department of Mathematics

Cite this document

Ćorić, M. (2020). Generativni modeli u dubokom strojnom učenju (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:383381

Ćorić, Mate. "Generativni modeli u dubokom strojnom učenju." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:383381

Ćorić, Mate. "Generativni modeli u dubokom strojnom učenju." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:383381

Ćorić, M. (2020). 'Generativni modeli u dubokom strojnom učenju', Master's thesis, University of Split, Faculty of Science, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:166:383381

Ćorić M. Generativni modeli u dubokom strojnom učenju [Master's thesis]. Split: University of Split, Faculty of Science; 2020 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:166:383381

M. Ćorić, "Generativni modeli u dubokom strojnom učenju", Master's thesis, University of Split, Faculty of Science, Split, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:166:383381

Please login to the repository to save this object to your list.
Metadata
TitleGenerativni modeli u dubokom strojnom učenju
Title (english)Deep generative models
AuthorMate Ćorić
MentorŽeljko Agić (mentor)
Committee memberŽeljko Agić (predsjednik povjerenstva)
Committee memberJurica Perić (član povjerenstva)
Committee memberAljoša Šubašić (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Mathematics)
Split
Defense date and country2020-09-09, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Generativni modeli su trenutno jedan od dominantnih pristupa modeliranju podataka koji imaju kompleksnu strukturu. Ova klasa modela predstavlja korak naprijed prema ostvarivanju inteligentnih sustava koji informacije o svom okruženju uče tako da stvaraju nove podatke. U ovom radu najviše pažnje je posvećeno najpopularnijim i trenutno najuspješnijim generativnim modelima: varijacijskim autoenkoderima i generativnim suparničkim mrežama. Naglasak je na matematičkoj pozadini algoritama i intuiciji iza njihovog dizajna. U drugom dijelu rada opisan je generativni nadzirani model i eksperimenti u Pythonu primijenjeni na MNIST skup podataka.
Abstract (english)
Generative models are currently one of the dominant approaches for modeling data with complex structure. This class of models is a step forward in the realization of intelligent systems that learn information about their environment by creating new data. In this thesis, the most attention is given to the two most popular and currently most successful deep generative models: variational autoencoders and generative adversarial networks. The emphasis is on the mathematical background of the algorithms and the intuition behind their design. Generative supervised model and experiments in Python applied to MNIST dataset are described in the second part of the thesis.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:383381
Study programmeTitle: Mathematics; specializations in: major in pure mathematics, major in computing, major in teaching, major in statistics and computing
Course: major in computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-02-02 15:07:01