prikaz prve stranice dokumenta Usporedba algoritama neuronskih mreža
  Download
PDF 1.75 MB
undergraduate thesis
Usporedba algoritama neuronskih mreža
2021. urn:nbn:hr:211:131317
Đuranec, Erik
University of Zagreb
Faculty of Organization and Informatics
Department of Information Systems Development

Cite this document

Đuranec, E. (2021). Usporedba algoritama neuronskih mreža (Undergraduate thesis). Varaždin: University of Zagreb, Faculty of Organization and Informatics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:211:131317

Đuranec, Erik. "Usporedba algoritama neuronskih mreža." Undergraduate thesis, University of Zagreb, Faculty of Organization and Informatics, 2021. https://urn.nsk.hr/urn:nbn:hr:211:131317

Đuranec, Erik. "Usporedba algoritama neuronskih mreža." Undergraduate thesis, University of Zagreb, Faculty of Organization and Informatics, 2021. https://urn.nsk.hr/urn:nbn:hr:211:131317

Đuranec, E. (2021). 'Usporedba algoritama neuronskih mreža', Undergraduate thesis, University of Zagreb, Faculty of Organization and Informatics, accessed 06 May 2024, https://urn.nsk.hr/urn:nbn:hr:211:131317

Đuranec E. Usporedba algoritama neuronskih mreža [Undergraduate thesis]. Varaždin: University of Zagreb, Faculty of Organization and Informatics; 2021 [cited 2024 May 06] Available at: https://urn.nsk.hr/urn:nbn:hr:211:131317

E. Đuranec, "Usporedba algoritama neuronskih mreža", Undergraduate thesis, University of Zagreb, Faculty of Organization and Informatics, Varaždin, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:211:131317

Please login to the repository to save this object to your list.
Metadata
TitleUsporedba algoritama neuronskih mreža
Title (english)Comparison of neural network algorithms
AuthorErik Đuranec
MentorDijana Oreški (mentor)
MBZ: 318615
Committee memberBožidar Kliček (član povjerenstva)
MBZ: 95426
GranterUniversity of Zagreb
Faculty of Organization and Informatics
(Department of Information Systems Development)
Varaždin
Defense date and country2021-09-10, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Organization and Informatics
Abstract
Ovaj rad se bavi tematikom neuronskih mreža od teoretskog aspekta pa sve do uspoređivanja konkretnih algoritama učenja. Preciznije, ovaj rad se dotiče fundamentalnih osnova i principa funkcioniranja neuronske mreže od umjetnog neurona preko aktivacijskih funkcija i mrežnih topologija pa sve do algoritama učenja. Naravno, postoje mnogi algoritmi koji su zaduženi za funkcioniranje neuronske mreže, ali mi ćemo u ovome radu fokus staviti na četiri algoritma učenja. Konkretno, usporedit ćemo performanse algoritma gradijentnog spusta, konjugiranog gradijentnog spusta, Quasi-Newton metode te Levenberg-Marquardt algoritma kao algoritama treniranja ili učenja neuronske mreže. Pritom je arhitektura neuronske mreže koju koristimo fiksna kako bi ostale varijable, izuzev samih algoritama učenja, ostale kontrolirane. Naposljetku se izvodi zaključak o performansama pojedinog algoritma uz preporuke za odabir istog.
Keywords
Languagecroatian
URN:NBNurn:nbn:hr:211:131317
Study programmeTitle: Business Systems
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0) icon
Created on2021-09-13 04:13:35