Learning of Radial Basis Function Networks: Experimental Results

0404841 - UIVT-O 20020210 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Neruda, Roman
Learning of Radial Basis Function Networks: Experimental Results.
Recent Advances in Computers, Computing and Communications. World Scientific and Engineering Society Press, 2002 - (Mastorakis, N.; Mladenov, V.), s. 241-246. ISBN 960-8052-62-9.
[World Multi-Conference on Circuits, Systems, Communications and Computeers /6./. Rethymno (GR), 07.07.2002-12.07.2002]
Grant CEP: GA ČR GA201/01/1192; GA AV ČR IAB1030006
Výzkumný záměr: AV0Z1030915
Klíčová slova: radial basis function networks * hybrid learning * soft computing
Kód oboru RIV: BA - Obecná matematika

We present various learning methods for RBF networks. The standard gradient-based learning is augmented by the weighted norm adaptation. The three-step learning algorithm uses different unsupervised learning algorithms for setting the centroids. Two possible combinations with genetic learning algorithm are considered as well. All learning variants are thoroughly compared on two benchmark tasks.
Trvalý link: http://hdl.handle.net/11104/0125071