prikaz prve stranice dokumenta Analiza slika očne pozadine dubokim neuronskim mrežama
No public access
master's thesis
Analiza slika očne pozadine dubokim neuronskim mrežama
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. urn:nbn:hr:168:939362
Ivančić, Kristijan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ivančić, K. (2016). Analiza slika očne pozadine dubokim neuronskim mrežama (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:939362

Ivančić, Kristijan. "Analiza slika očne pozadine dubokim neuronskim mrežama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:939362

Ivančić, Kristijan. "Analiza slika očne pozadine dubokim neuronskim mrežama." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:939362

Ivančić, K. (2016). 'Analiza slika očne pozadine dubokim neuronskim mrežama', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:939362

Ivančić K. Analiza slika očne pozadine dubokim neuronskim mrežama [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2016 [cited 2024 November 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:939362

K. Ivančić, "Analiza slika očne pozadine dubokim neuronskim mrežama", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2016. Available at: https://urn.nsk.hr/urn:nbn:hr:168:939362

Metadata
TitleAnaliza slika očne pozadine dubokim neuronskim mrežama
Title (english)Retinal image analysis using deep neural networks
AuthorKristijan Ivančić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberDavor Petrinović (član povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2016-07-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu opisan je proces dubokog učenja korištenjem umjetnih neuronskih mreža, s posebnim naglaskom na konvolucijske neuronske mreže. Izložen je problem automatske detekcije dijabetičke retinopatije te prikazano jedno njegovo moguće rješenje korištenjem konvolucijskih mreža. U Caffe radnoj okolini dizajnirano je i trenirano nekoliko mreža različitih arhitektura nad skupom podataka dobivenog sa Kaggle natjecanja u automatskoj detekciji dijabetičke retinopatije. Prikazani su rezultati mreža u ovisnosti o arhitekturi i različitim vrijednostima parametara učenja metodom stohastičkog gradijentnog spusta.
Abstract (english)
This work describes the process of deep learning using artificial neural networks, with emphasis on convolutional networks. One posible solution is given to the problem of automated detection of diabetic retinopathy, using convolutional networks. Datasets were obtained from the Kaggle Diabetic Retinopathy Challenge, and a solution was implemented in the Caffe deep learning framework. Multiple networks with different architectures were designed and trained. The results of these networks are shown in relation to variations in hyperparameters of the stohastic gradient descent learning algorithm.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:939362
Study programmeTitle: Information and Communication Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-19 13:34:43