A fast and efficient algorithm for training radial basis function neural networks based on a fuzzy partition of the input space

Sarimveis, H; Alexandridis, A; Tsekouras, G; Bafas, G

dc.contributor.author	Sarimveis, H	en
dc.contributor.author	Alexandridis, A	en
dc.contributor.author	Tsekouras, G	en
dc.contributor.author	Bafas, G	en
dc.date.accessioned	2014-03-01T01:17:20Z
dc.date.available	2014-03-01T01:17:20Z
dc.date.issued	2002	en
dc.identifier.issn	0888-5885	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/14472
dc.subject	Efficient Algorithm	en
dc.subject	Radial Basis Function Neural Network	en
dc.subject.classification	Engineering, Chemical	en
dc.subject.other	Fuzzy partitions	en
dc.subject.other	Algorithms	en
dc.subject.other	Computer simulation	en
dc.subject.other	Neural networks	en
dc.subject.other	Chemical engineering	en
dc.subject.other	neural network	en
dc.subject.other	algorithm	en
dc.subject.other	architecture	en
dc.subject.other	article	en
dc.subject.other	control system	en
dc.subject.other	dynamics	en
dc.subject.other	error	en
dc.subject.other	learning	en
dc.subject.other	mathematical analysis	en
dc.subject.other	mathematical model	en
dc.subject.other	methodology	en
dc.subject.other	organization	en
dc.subject.other	space	en
dc.subject.other	structure analysis	en
dc.subject.other	technique	en
dc.subject.other	training	en
dc.title	A fast and efficient algorithm for training radial basis function neural networks based on a fuzzy partition of the input space	en
heal.type	journalArticle	en
heal.identifier.primary	10.1021/ie010263h	en
heal.identifier.secondary	http://dx.doi.org/10.1021/ie010263h	en
heal.language	English	en
heal.publicationDate	2002	en
heal.abstract	The popular radial basis function (RBF) neural network architecture and a new fast and efficient method for training such a network are used to model nonlinear dynamical multi-input multi-output (MIMO) discrete-time systems. The proposed training methodology is based on a fuzzy partition of the input space and combines self-organized and supervised learning. The algorithm is illustrated through the development of neural network models using simulated and experimental data. Results show that the methodology is much faster and produces more accurate models compared to the standard techniques used to train RBF networks. Another important advantage is that, for a given fuzzy partition of the input space, the proposed method is able to determine the proper network structure, without using a trial and error procedure.	en
heal.publisher	AMER CHEMICAL SOC	en
heal.journalName	Industrial and Engineering Chemistry Research	en
dc.identifier.doi	10.1021/ie010263h	en
dc.identifier.isi	ISI:000173965700013	en
dc.identifier.volume	41	en
dc.identifier.issue	4	en
dc.identifier.spage	751	en
dc.identifier.epage	759	en