prikaz prve stranice dokumenta Primjena strojnog učenja u klasificiranju LEGO kocaka
  Download
PDF 1.35 MB
undergraduate thesis
Primjena strojnog učenja u klasificiranju LEGO kocaka
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. urn:nbn:hr:200:859496
Hamzić, Ervin
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Hamzić, E. (2018). Primjena strojnog učenja u klasificiranju LEGO kocaka (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:859496

Hamzić, Ervin. "Primjena strojnog učenja u klasificiranju LEGO kocaka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:859496

Hamzić, Ervin. "Primjena strojnog učenja u klasificiranju LEGO kocaka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:859496

Hamzić, E. (2018). 'Primjena strojnog učenja u klasificiranju LEGO kocaka', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:859496

Hamzić E. Primjena strojnog učenja u klasificiranju LEGO kocaka [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:200:859496

E. Hamzić, "Primjena strojnog učenja u klasificiranju LEGO kocaka", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:859496

Metadata
TitlePrimjena strojnog učenja u klasificiranju LEGO kocaka
Title (english)LEGO Bricks Classification with Machine Learning
AuthorErvin Hamzić
MentorJosip Job (mentor)
Committee memberJosip Job (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberEmmanuel Karlo Nyarko (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2018-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Rad donosi teorijsku pozadinu potrebnu za razumijevanje funkcioniranja i realizacije konvolucijskih neuronskih mreža, danas najzastupljenije metode dubokog učenja na problemima klasifikacije slikovnih podataka. Cilj rada bio je demonstrirati izradu konvolucijske neuronske mreže za rješavanje problema klasifikacije slika LEGO kocaka. U rješavanju zadatka korištene su tehnologije TensorFlow i Keras pomoću kojih je neuronska mreža dizajnirana, trenirana i evaluirana. Na samom kraju rada opisani dobiveni rezultati i zaključci.
Abstract (english)
This work presents the theoretical background required in order to understand the way of functioning and implementation of convolutional neural networks which are the most widely used method of deep learning applied for image classification problems nowadays. The aim of this work was to demonstrate the design of a convolutional neural network applied on a LEGO brick image classification problem. TensorFlow and Keras were the technologies used in solving this task and by means of which the neural network was designed, trained and evaluated. The results and conclusions are described in the final part of the work.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:859496
Study programmeTitle: Undergraduate University Study Programme
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-10-23 10:40:47