prikaz prve stranice dokumenta Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu
  Download
PDF 3.65 MB
master's thesis
Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu
2021. urn:nbn:hr:200:535168
Štajnbrikner, Matej
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Electronics and Microelectronics

Cite this document

Štajnbrikner, M. (2021). Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu (Master's 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:200:535168

Štajnbrikner, Matej. "Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:535168

Štajnbrikner, Matej. "Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:535168

Štajnbrikner, M. (2021). 'Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 29 March 2025, https://urn.nsk.hr/urn:nbn:hr:200:535168

Štajnbrikner M. Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2025 March 29] Available at: https://urn.nsk.hr/urn:nbn:hr:200:535168

M. Štajnbrikner, "Implementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:535168

Please login to the repository to save this object to your list.
Metadata
TitleImplementacija neuronske mreže za prepoznavanje znamenki u FPGA sustavu
Title (english)Implementation of a neural network for digit recognition in FPGA system
AuthorMatej Štajnbrikner
MentorTomislav Matić (mentor)
Committee memberTomislav Matić (predsjednik povjerenstva)
Committee memberMario Vranješ (član povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Electronics and Microelectronics)
Osijek
Defense date and country2021-09-10, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Electronics
Abstract
U okviru ovog rada opisana je implementacija sustava za prepoznavanje ručno pisanih znamenki u FPGA sustavu. Na početku su opisane vrste neuronskih mreža koje postižu najbolje rezultate u rješavanju problema prepoznavanja znamenaka, a zatim je dan pregled postojećih rješenja. Nakon toga je opisan model neuronske mreže te je dana teorija iza algoritma propagacije unaprijed i propagacije unazad. Zatim slijedi opis implementacije sustava koja podrazumijeva opis korištenih alata i tehnologija te opis svih komponenti sustava, sustava u cjelini i programske podrške. Na kraju rada predstavljeni su rezultati mjerenja te je provedena evaluacija.
Abstract (english)
This paper describes the implementation of a system for recognizing handwritten digits in an FPGA system. At the beginning, the types of neural networks that achieve the best results in solving the problem of digit recognition are described, and then an overview of existing solutions is given. After that, the neural network model is described and the theory behind the algorithm of forward propagation and backward propagation is given. This is followed by a description of the implementation of the system, which includes a description of the tools and technologies used and description of all components of the system, the system as whole and software. At the end of the paper, the measurement results were presented and an evaluation was performed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:535168
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-10-05 12:54:55