prikaz prve stranice dokumenta Modeliranje i simulacija neuronskih mreža koristeći Matlab
  Download
PDF 584.82 KB
undergraduate thesis
Modeliranje i simulacija neuronskih mreža koristeći Matlab
2024. urn:nbn:hr:200:675872
Ružman, Lovro
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Ružman, L. (2024). Modeliranje i simulacija neuronskih mreža koristeći Matlab (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:200:675872

Ružman, Lovro. "Modeliranje i simulacija neuronskih mreža koristeći Matlab." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:675872

Ružman, Lovro. "Modeliranje i simulacija neuronskih mreža koristeći Matlab." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:675872

Ružman, L. (2024). 'Modeliranje i simulacija neuronskih mreža koristeći Matlab', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 05 April 2025, https://urn.nsk.hr/urn:nbn:hr:200:675872

Ružman L. Modeliranje i simulacija neuronskih mreža koristeći Matlab [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2024 [cited 2025 April 05] Available at: https://urn.nsk.hr/urn:nbn:hr:200:675872

L. Ružman, "Modeliranje i simulacija neuronskih mreža koristeći Matlab", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:200:675872

Please login to the repository to save this object to your list.
Metadata
TitleModeliranje i simulacija neuronskih mreža koristeći Matlab
Title (english)Modeling and simulation of neural networks using Matlab
AuthorLovro Ružman
MentorMirko Köhler (mentor)
Committee memberRobert Cupec (predsjednik 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 country2024-09-25, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U završnom radu istražena je primjena neuronskih mreža u MATLAB-u kroz laboratorijsku vježbu usmjerenu na jedan konkretan primjer. Glavni problem rada bio je razvoj i evaluacija neuronske mreže za klasifikaciju slika, s ciljem postizanja visoke točnosti u prepoznavanju predmeta na slikama. Za rješavanje ovog problema korišten je alat Deep Network Designer unutar MATLAB a za izgradnju i obuku neuronske mreže. Proces je obuhvaćao pripremu skupa podataka, konstrukciju modela, trening mreže i evaluaciju rezultata. Kroz laboratorijsku vježbu, implementiran je jednostavan primjer klasifikacije slika rukom pisanih brojeva, gdje su se prikazali svi ključni koraci od učitavanja podataka do evaluacije performansi modela. Postignuti rezultati uključuju visoku točnost klasifikacije modela, što potvrđuje učinkovitost pristupa primijenjenog u radu. Ovaj primjer pokazuje praktične aspekte primjene neuronskih mreža u MATLAB-u i pruža osnovu za daljnje istraživanje i primjenu u stvarnim scenarijima.
Abstract (english)
Modeling and simulation of neural networks using MATLAB This final paper explores the application of neural networks in MATLAB through a laboratory exercise focused on a specific example. The main problem addressed was the development and evaluation of a neural network for image classification, with the goal of achieving high accuracy in object recognition within images. To tackle this problem, the Deep Network Designer tool within MATLAB was used to build and train the neural network. The process included data preparation, model construction, network training, and result evaluation. The laboratory exercise implemented a simple example of classifying handwritten digits, demonstrating all key steps from data loading to performance evaluation of the model. The achieved results include high classification accuracy, confirming the effectiveness of the approach applied in the work. This example illustrates the practical aspects of using neural networks in MATLAB and provides a foundation for further research and application in real-world scenarios.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:675872
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-10-24 08:04:47