prikaz prve stranice dokumenta Klasifikacija objekata mobilnim uređajem
Access restricted to students and staff of home institution
master's thesis
Klasifikacija objekata mobilnim uređajem
Split: University of Split, University of Split, Faculty of science, 2020. urn:nbn:hr:166:623163
Babić, Iliana
University of Split
Faculty of Science
Department of Informatics

Institutional repository: Repository of Faculty of Science

Cite this document

Babić, I. (2020). Klasifikacija objekata mobilnim uređajem (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:623163

Babić, Iliana. "Klasifikacija objekata mobilnim uređajem." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:623163

Babić, Iliana. "Klasifikacija objekata mobilnim uređajem." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:623163

Babić, I. (2020). 'Klasifikacija objekata mobilnim uređajem', Master's thesis, University of Split, Faculty of Science, accessed 04 September 2024, https://urn.nsk.hr/urn:nbn:hr:166:623163

Babić I. Klasifikacija objekata mobilnim uređajem [Master's thesis]. Split: University of Split, Faculty of Science; 2020 [cited 2024 September 04] Available at: https://urn.nsk.hr/urn:nbn:hr:166:623163

I. Babić, "Klasifikacija objekata mobilnim uređajem", Master's thesis, University of Split, Faculty of Science, Split, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:166:623163

Metadata
TitleKlasifikacija objekata mobilnim uređajem
Title (english)Object classification on mobile devices
AuthorIliana Babić
MentorSaša Mladenović (mentor)
Committee memberSaša Mladenović (predsjednik povjerenstva)
Committee memberGoran Zaharija (član povjerenstva)
Committee memberDivna Krpan (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2020-07-29, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu se definira problem i rješenje klasifikacije objekata koristeći transfer learning. U prvom dijelu, naglasak je na umjetnoj inteligenciji, njenom razvoju, primjeni te na strojnom i dubinskom učenju. Definiraju se neuronske mrežu, njihova svrha, struktura, problemi kojima se oni bave, te objašnjava proces treniranja. Konvolucijske neuronske mreže su detaljnije objašnjene preko primjera klasifikacije slike. Drugi dio rada se fokusira na transfer learning i njegovu primjenu na problemu klasifikacije. Objašnjava se njegova smisao, vrste pristupa, proces koji se odvija te se prelazi na praktični dio. Navodi se razvojno okruženje koje je korišteno. Opisuje se ideja projekta, tijek izrade i problematika, teorijski te preko isječaka koda i prikazan završni rezultat.
Abstract (english)
This paper discusses the problem and solution of object classification using transfer learning. In the first part, the emphasis is on artificial intelligence, its development, application, and on machine and deep learning. Neural networks are defined, their purpose, structure, problems which they deal with and their training process is explained. Convolutional neural networks are explained in more detail through an image classification example. The second part of the paper focuses on transfer learning and its application to the problem of classification. It explains its purpose, types of approaches, the process that takes place and moves on to the practical part. The used development environment is stated. The idea of the project, the course of development and problems are described, theoretically and through code snippets, and the final result is presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:623163
Study programmeTitle: Computer Science; specializations in: major in teaching
Course: major in teaching
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra edukacije informatike (magistar/magistra edukacije informatike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-02-03 10:40:00