Learning algorithms for neural networks with the Kalman filters

Watanabe, K; Tzafestas, SG

dc.contributor.author	Watanabe, K	en
dc.contributor.author	Tzafestas, SG	en
dc.date.accessioned	2014-03-01T01:08:00Z
dc.date.available	2014-03-01T01:08:00Z
dc.date.issued	1990	en
dc.identifier.issn	0921-0296	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/10242
dc.subject	Kalman filters	en
dc.subject	learning systems	en
dc.subject	Neural nets	en
dc.subject	nonlinear filtering	en
dc.subject	parameter estimation	en
dc.subject	pattern recognition	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Robotics	en
dc.title	Learning algorithms for neural networks with the Kalman filters	en
heal.type	journalArticle	en
heal.identifier.primary	10.1007/BF00439421	en
heal.identifier.secondary	http://dx.doi.org/10.1007/BF00439421	en
heal.language	English	en
heal.publicationDate	1990	en
heal.abstract	Based on various approaches, several different learing algorithms have been given in the literature for neural networks. Almost all algorithms have constant learning rates or constant accelerative parameters, though they have been shown to be effective for some practical applications. The learning procedure of neural networks can be regarded as a problem of estimating (or identifying) constant parameters (i.e. connection weights of network) with a nonlinear or linear observation equation. Making use of the Kalman filtering, we derive a new back-propagation algorithm whose learning rate is computed by a time-varying Riccati difference equation. Perceptron-like and correlational learning algorithms are also obtained as special cases. Furthermore, a self-organising algorithm of feature maps is constructed within a similar framework. © 1990 Kluwer Academic Publishers.	en
heal.publisher	Kluwer Academic Publishers	en
heal.journalName	Journal of Intelligent and Robotic Systems	en
dc.identifier.doi	10.1007/BF00439421	en
dc.identifier.isi	ISI:A1990ER31600002	en
dc.identifier.volume	3	en
dc.identifier.issue	4	en
dc.identifier.spage	305	en
dc.identifier.epage	319	en