prikaz prve stranice dokumenta Randomizirana metoda optimizacije ADAM
  Download
PDF 1.29 MB
master's thesis
Randomizirana metoda optimizacije ADAM
Zagreb: University of Zagreb, Faculty of Science, 2023. urn:nbn:hr:217:188192
Marić, Igor
University of Zagreb
Faculty of Science
Department of Mathematics

Institutional repository: Repository of the Faculty of Science

Cite this document

Marić, I. (2023). Randomizirana metoda optimizacije ADAM (Master's thesis). Zagreb: University of Zagreb, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:217:188192

Marić, Igor. "Randomizirana metoda optimizacije ADAM." Master's thesis, University of Zagreb, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:217:188192

Marić, Igor. "Randomizirana metoda optimizacije ADAM." Master's thesis, University of Zagreb, Faculty of Science, 2023. https://urn.nsk.hr/urn:nbn:hr:217:188192

Marić, I. (2023). 'Randomizirana metoda optimizacije ADAM', Master's thesis, University of Zagreb, Faculty of Science, accessed 24 August 2024, https://urn.nsk.hr/urn:nbn:hr:217:188192

Marić I. Randomizirana metoda optimizacije ADAM [Master's thesis]. Zagreb: University of Zagreb, Faculty of Science; 2023 [cited 2024 August 24] Available at: https://urn.nsk.hr/urn:nbn:hr:217:188192

I. Marić, "Randomizirana metoda optimizacije ADAM", Master's thesis, University of Zagreb, Faculty of Science, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:217:188192

Metadata
TitleRandomizirana metoda optimizacije ADAM
Title (english)Randomized optimization method ADAM
AuthorIgor Marić
MentorLuka Grubišić (mentor)
Committee memberLuka Grubišić (predsjednik povjerenstva)
Committee memberZvonimir Bujanović (član povjerenstva)
Committee memberMladen Vuković (član povjerenstva)
Committee memberIgor Ciganović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Science
(Department of Mathematics)
Zagreb
Defense date and country2023-05-04, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Abstract
U ovom radu obrađene su stohastičke gradijentne metode. Analizu smo većinom sproveli na metodi linearne regresije. Svi opimizatori su zbog te svrhe implementirani. Iz primjera smo vidjeli da se u preciznosti i efikasnosti najviše iskazala metoda adaptivnog reduciranja varijance Adam. Potom, opisali smo biblioteke automatskog deriviranja koda Jax i Autograd te na osnovu njih uvidjeli znatnu olakšicu u primjenama optimizatora. Naposljetku, implementirali smo algoritam za restauraciju slika naziva HRMC.
Abstract (english)
This thesis deals with stochastic gradient methods. We mostly conducted the analysis using the linear regression method. All optimizers are implemented for this purpose. From the examples, we saw that the method of adaptive variance reduction Adam was the most accurate and efficient. Then, we described the automatic code derivation libraries Jax and Autograd, and based on them, we saw a significant improvement in optimizer applications. Finally, we implemented an image restoration algorithm called HRMC.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:217:188192
Study programmeTitle: Computer Science and Mathematics
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni magistar računarstva i matematike (sveučilišni magistar računarstva i matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-02-09 12:40:52