prikaz prve stranice dokumenta KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA
Access restricted to students and staff of home institution
master's thesis
KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA
Slavonski Brod: Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod, 2020. urn:nbn:hr:153:523623
Eljuga, Jure
Josip Juraj Strossmayer University of Osijek
Mechanical Engineering Faculty in Slavonski Brod

Institutional repository: Repository of Mechanical Engineering in Slavonski Brod

Cite this document

Eljuga, J. (2020). KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA (Master's thesis). Slavonski Brod: Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod. Retrieved from https://urn.nsk.hr/urn:nbn:hr:153:523623

Eljuga, Jure. "KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA." Master's thesis, Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod, 2020. https://urn.nsk.hr/urn:nbn:hr:153:523623

Eljuga, Jure. "KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA." Master's thesis, Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod, 2020. https://urn.nsk.hr/urn:nbn:hr:153:523623

Eljuga, J. (2020). 'KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA', Master's thesis, Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:153:523623

Eljuga J. KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA [Master's thesis]. Slavonski Brod: Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod; 2020 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:153:523623

J. Eljuga, "KORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA", Master's thesis, Josip Juraj Strossmayer University of Osijek, Mechanical Engineering Faculty in Slavonski Brod, Slavonski Brod, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:153:523623

Metadata
TitleKORIŠTENJE UMJETNIH NEURONSKIH MREŽA U PROBLEMIMA PREPOZNAVANJA
Title (english)USE OF ARTIFICIAL NEURAL NETWORKS IN RECOGNITION PROBLEMS
AuthorJure Eljuga
MentorTomislav Šarić (mentor)
Committee memberTomislav Šarić (član povjerenstva)
Committee memberGoran Šimunović (predsjednik povjerenstva)
Committee memberRoberto Lujić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Mechanical Engineering Faculty in Slavonski Brod
Slavonski Brod
Defense date and country2020-07-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Umjetne neuronske mreže su zanimljivo područje suvremene umjetne inteligencije i danas su predmet brojnih znanstvenih istraživanja. Rade na principu oponašanja obrade podataka koja se odvija u biološkom neuronu. Svaki umjetni neuron prima ulazne podatke, obrađuje ih matematičkim funkcijama i daje rezultirajuće izlazne podatke. Izlaz neuronske mreže uspoređuje se s traženim izlazom i na temelju odstupanja rezultata (greške) podešavaju se određeni parametri neuronske mreže kako bi se greška smanjila. Neuronske mreže imaju visok potencijal za rješavanje problema prepoznavanja. U ovom radu istražio se okvir Neuroph Framework za oblikovanje umjetnih neuronskih mreža i mogućnost primjene neuronskih mreža oblikovanih u programu Neuroph Studio u rješavanju problema prepoznavanja.
Abstract (english)
Artificial neural networks are an interesting domain of modern artificial intelligence and they are often found as subjects of scientific research of today. They operate by imitating data processing as it occurs in a biological neuron. Every artificial neuron receives input data, processes it via mathematical functions and outputs output data. Neural network output is compared to the desired output and based on the deviation of results (error), certain network parameters are adjusted in order to lower the error. Neural networks possess high potential for solving issues in recognition. This paper presents an investigative look into a framework for creating artificial neural networks called Neuroph Framework and the possibility of use of neural networks created in Neuroph Studio for solving issues in recognition.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:153:523623
Study programmeTitle: Graduate Study Mechanical Engineering; specializations in: Design and Product Development, Manufacturing Logistics, Materials Engineering, Engineering Technologies, Power Engineering
Course: Design and Product Development
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-09-09 12:20:22