Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima

Sečan, Krešimir

undergraduate thesis

Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima

Osijek: Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, 2024. urn:nbn:hr:126:464557

Sečan, Krešimir

Josip Juraj Strossmayer University of Osijek
School of Applied Mathematics and Informatics

Cite this document

APA 6th Edition

Sečan, K. (2024). Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:464557

MLA 8th Edition

Sečan, Krešimir. "Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, 2024. https://urn.nsk.hr/urn:nbn:hr:126:464557

Chicago 17th Edition

Harvard

Sečan, K. (2024). 'Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, accessed 18 November 2024, https://urn.nsk.hr/urn:nbn:hr:126:464557

Vancouver

Sečan K. Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics; 2024 [cited 2024 November 18] Available at: https://urn.nsk.hr/urn:nbn:hr:126:464557

IEEE

K. Sečan, "Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:126:464557

Cite this item: https://urn.nsk.hr/urn:nbn:hr:126:464557

Please login to the repository to save this object to your list.

Metadata

Title	Usporedba klasičnih algoritama strojnog učenja i neuronske mreže u klasifikacijskim problemima
Title (english)	Comparison of Traditional Machine Learning Algorithms and Neural Network in Classification Problems
Author	Krešimir Sečan
Mentor	Domagoj Matijević (mentor)
Granter	Josip Juraj Strossmayer University of Osijek School of Applied Mathematics and Informatics Osijek
Defense date and country	2024-09-17, Croatia
Scientific / art field, discipline and subdiscipline	NATURAL SCIENCES Mathematics Mathematical Logic and Accounting
Abstract	U ovom radu razmotrit ćemo zadatke klasifikacije, opisati neke od algoritama koji se koriste za klasifikaciju te opisati neuronsku mrežu. Nakon toga, implementirat ćemo i istrenirati modele za algoritam logističke regresije, metode potpornih vektora i neuronsku mrežu na MNIST skupu podataka. Na kraju, evaluirat ćemo modele na testnom skupu podataka i provesti njihovu usporedbu.
Abstract (english)	In this paper, we will examine classification tasks, describe some of the algorithms used for classification, and provide an overview of neural networks. Following that, we will implement and train models for logistic regression, support vector machine, and neural networks using the MNIST dataset. Finally, we will evaluate the models on a test dataset and compare them.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:126:464557
Study programme	Title: Bachelor of Mathematics and Computer Science Study programme type: university Study level: undergraduate Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Repository	Repository of School of Applied Mathematics and Informatics
Created on	2024-09-20 10:10:36