Contribution to the Combined Learning Algorithm for RBF Neural Network (CROSBI ID 475459)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Brezak, Danko ; Novaković, Branko ; Majetić, Dubravko
engleski
Contribution to the Combined Learning Algorithm for RBF Neural Network
This paper presents contribution to the combined learning method for Radial Basis Function (RBF) neural network in the sense of introducing another way for the (RBF) network structure determination. Instead of using only K-means clustering method for disposing the network structure, the modified method based on neurone centre membership parameter beta_Ais proposed. In many cases this method leads toward better solutions with a special emphasis on approximation problems.
Radial Basis Function Network; Combined learning method; Modified method; Approximation
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
047-048-x.
2000.
objavljeno
Podaci o matičnoj publikaciji
11th International DAAAM Symposium "Intelligent Manufacturing & Automation: Man - Machine - Nature"
Katalinic, Branko
Beč: DAAAM International Vienna
Podaci o skupu
11th International DAAAM Symposium "INTELLIGENT MANUFACTURING & AUTOMATION: MAN-MACHINE-NATURE"
predavanje
19.10.2000-21.10.2000
Opatija, Hrvatska