prikaz prve stranice dokumenta Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže
  Download
PDF 1.5 MB
undergraduate thesis
Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže
2015. urn:nbn:hr:235:188984
Murat, Zrinka
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Cite this document

Murat, Z. (2015). Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:188984

Murat, Zrinka. "Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2015. https://urn.nsk.hr/urn:nbn:hr:235:188984

Murat, Zrinka. "Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2015. https://urn.nsk.hr/urn:nbn:hr:235:188984

Murat, Z. (2015). 'Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže', Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 03 December 2024, https://urn.nsk.hr/urn:nbn:hr:235:188984

Murat Z. Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2015 [cited 2024 December 03] Available at: https://urn.nsk.hr/urn:nbn:hr:235:188984

Z. Murat, "Utjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže", Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:235:188984

Please login to the repository to save this object to your list.
Metadata
TitleUtjecaj parametara aktivacijskih funkcija na odziv RBF neuronske mreže
Title (english)The influence of activation function parameters on the performance of RBF neural network
AuthorZrinka Murat
MentorDanko Brezak (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2015-03-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Ovaj rad temelji se na analizi karakteristika RBF neuronske mreže zasnovane na trima različitim aktivacijskim funkcijama: Gaussovoj, inverznoj kvadratnoj i trokutnoj. Generalizacijska svojstva mreže ispitana su za sve tri spomenute funkcije, te uz varijacije u iznosima parametra grupiranja i širina aktivacijskih funkcija Procesi učenja i testiranja provedeni su korištenjem dva aproksimacijska i dva klasifikacijska problema.
Abstract (english)
The aim of this thesis is to analyse characteristics of RBF neural network structured with the following three activation functions: Gaussian, inverse quadratic and triangular. Generalization characteristics were tested and compared for several network configurations, which were characterized not only by the types of activation functions, but also by their varying widths and positions, as well as hidden layer neurons number. Processes of learning and testing were performed on two approximation and two classification problems.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:188984
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-05-22 12:48:05