Naslov
Neiterativni postupak učenja parametara neuronskih mreža
(Noniterative approach to learning of neural network parameters)

Autori
Široki, Mladen

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, doktorska disertacija

Fakultet
Strojarstva i brodogradnje

Mjesto
Zagreb

Datum
07.03

Godina
1996

Stranica
118

Mentor
Novaković, Branko

Ključne riječi
Neuronske mreže; radijalne bazne finkcije; neiterativno učenje
(Neural networks; radial basis functions (RBF); noniterative learning)

Sažetak
The basic idea of this work is that in classification problems better results can be achieved if each hidden unit has its own matrix W for calculation of weighted distances. In this case hidden layer parameters (matrices W and positions of the centres t) can be learned much faster, locally, for each class of the problem separately, using well known statistical methods, than by optimization process proposed by Poggio and Girosi. With chosen hidden layer parameters optimal linear output layer weights can be calculated in single step (noniterative approach) using all training samples.

Izvorni jezik
Hrvatski

Znanstvena područja
Strojarstvo

POVEZANOST RADA