prikaz prve stranice dokumenta Primjena neuralnih mreža u programskom jeziku Python
Access restricted to authenticated users
undergraduate thesis
Primjena neuralnih mreža u programskom jeziku Python
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. urn:nbn:hr:179:609737
Režić, Ante
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Režić, A. (2022). Primjena neuralnih mreža u programskom jeziku Python (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:609737

Režić, Ante. "Primjena neuralnih mreža u programskom jeziku Python." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:609737

Režić, Ante. "Primjena neuralnih mreža u programskom jeziku Python." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:609737

Režić, A. (2022). 'Primjena neuralnih mreža u programskom jeziku Python', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 16 June 2024, https://urn.nsk.hr/urn:nbn:hr:179:609737

Režić A. Primjena neuralnih mreža u programskom jeziku Python [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 June 16] Available at: https://urn.nsk.hr/urn:nbn:hr:179:609737

A. Režić, "Primjena neuralnih mreža u programskom jeziku Python", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:609737

Metadata
TitlePrimjena neuralnih mreža u programskom jeziku Python
Title (english)Usage of Neural Networks
AuthorAnte Režić
MentorDamir Krstinić https://orcid.org/0000-0002-9946-6630 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom završnom radu ispituju se neuronske mreže i njihova primjena u području računalnog vida. Ukratko je obrađena povijest neuronskih mreža i računalnog vida. Programski jezik Python opisuje se kao najbolji jezik za duboke neuronske mreže zbog svojih funkcionalnosti i pristupačnosti. Opisane su tri odvojene, ali slične neuronske mreže, kao i logika iza njihovog dizajna. Sve su tri mreže trenirane za klasificiranje pojedinaca u kategorije na temelju njihovog spola, rase i dobi, koristeći samo slike njihovih lica. Objašnjen je proces unazadne propagacije, kao i ideja koja stoji iza funkcija gubitaka. Pokazano je da tri modela rade na prethodno neviđenim slikama.
Abstract (english)
In this undergraduate thesis, neural networks, and how they are applied to computer vision, is examined. History of neural networks and computer vision is briefly discussed. Python programming language is described as the best language for deep neural networks due to its functionally and accessibility. Three separate but similar neural networks are described, as well as the logic behind their design. All three of them are trained to classify individuals into categories based on their gender, race and age, using only facial images. The process of backpropagation is explained as well as the idea behind loss functions. The three models are demonstrated to work on previously unseen images.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:609737
Study programmeTitle: Computing
Study programme type: professional
Study level: undergraduate
Academic / professional title: stručni/a prvostupnik/ prvostupnica inženjer/inženjerka računarstva (stručni/a prvostupnik/ prvostupnica inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-06-27 07:50:39