Pregled bibliografske jedinice broj: 47801
Contribution to the Combined Learning Algorithm for RBF Neural Network
Contribution to the Combined Learning Algorithm for RBF Neural Network // 11th International DAAAM Symposium "Intelligent Manufacturing & Automation: Man - Machine - Nature" / Katalinic, Branko (ur.).
Beč: DAAAM International Vienna, 2000. str. 047-048 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 47801 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Contribution to the Combined Learning Algorithm for RBF Neural Network
Autori
Brezak, Danko ; Novaković, Branko ; Majetić, Dubravko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
11th International DAAAM Symposium "Intelligent Manufacturing & Automation: Man - Machine - Nature"
/ Katalinic, Branko - Beč : DAAAM International Vienna, 2000, 047-048
Skup
11th International DAAAM Symposium "Intelligent Manufacturing & Automation: Man - Machine - Nature"
Mjesto i datum
Opatija, Hrvatska, 19.10.2000. - 21.10.2000
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Radial Basis Function Network; Combined learning method; Modified method; Approximation
Sažetak
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.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
