Training the random neural network using quasi-Newton methods

Likas, A; Stafylopatis, A

dc.contributor.author	Likas, A	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T01:15:57Z
dc.date.available	2014-03-01T01:15:57Z
dc.date.issued	2000	en
dc.identifier.issn	0377-2217	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13843
dc.subject	Gradient Descent Method	en
dc.subject	Optimization Technique	en
dc.subject	quasi-newton method	en
dc.subject	Quasi Newton	en
dc.subject	Random Neural Network	en
dc.subject.classification	Management	en
dc.subject.classification	Operations Research & Management Science	en
dc.subject.other	QUEUING-NETWORKS	en
dc.subject.other	OPTIMIZATION	en
dc.subject.other	CUSTOMERS	en
dc.title	Training the random neural network using quasi-Newton methods	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0377-2217(99)00482-8	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0377-2217(99)00482-8	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	Training in the random neural network (RNN) is generally specified as the minimization of an appropriate error function with respect to the parameters of the network (weights corresponding to positive and negative connections). We propose here a technique for error minimization that is based on the use of quasi-Newton optimization techniques. Such techniques offer more sophisticated exploitation of the gradient information compared to simple gradient descent methods, but are computationally more expensive and difficult to implement. In this work we specify the necessary details for the application of quasi-Newton methods to the training of the RNN, and provide comparative experimental results from the use of these methods to some well-known test problems, which confirm the superiority of the approach. (C) 2000 Elsevier Science B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	EUROPEAN JOURNAL OF OPERATIONAL RESEARCH	en
dc.identifier.doi	10.1016/S0377-2217(99)00482-8	en
dc.identifier.isi	ISI:000088925200008	en
dc.identifier.volume	126	en
dc.identifier.issue	2	en
dc.identifier.spage	331	en
dc.identifier.epage	339	en