Study of the generalization capability versus training in backpropagation neural networks

Dalianis, PJ; Tzafestas, SG; Anthopoulos, G

dc.contributor.author	Dalianis, PJ	en
dc.contributor.author	Tzafestas, SG	en
dc.contributor.author	Anthopoulos, G	en
dc.date.accessioned	2014-03-01T02:40:58Z
dc.date.available	2014-03-01T02:40:58Z
dc.date.issued	1993	en
dc.identifier.issn	08843627	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30297
dc.subject	backpropagation	en
dc.subject	backpropagation neural network	en
dc.subject	Dynamic Properties	en
dc.subject	Energy Function	en
dc.subject	Generalization Capability	en
dc.subject.other	Algorithms	en
dc.subject.other	Approximation theory	en
dc.subject.other	Degrees of freedom (mechanics)	en
dc.subject.other	Learning systems	en
dc.subject.other	Mathematical models	en
dc.subject.other	Numerical analysis	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Performance	en
dc.subject.other	Plasticity	en
dc.subject.other	Probability	en
dc.subject.other	Backpropagation neural networks	en
dc.subject.other	Energy function	en
dc.subject.other	Overtraining phenomenon	en
dc.subject.other	Probability density function	en
dc.subject.other	Neural networks	en
dc.title	Study of the generalization capability versus training in backpropagation neural networks	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICSMC.1993.390760	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICSMC.1993.390760	en
heal.publicationDate	1993	en
heal.abstract	In this paper, the phenomenon of overtraining in backpropagation neural networks is discussed. The relationships between network size, training set size and generalization capabilities are examined. An extension to an existing algorithm of backpropagation is described. The extended algorithm provides a new energy function and its advantages, such as improved plasticity and performance along with its dynamic properties, are explained. The algorithm is applied to some common problems and simulation results are presented and discussed.	en
heal.publisher	Publ by IEEE, Piscataway, NJ, United States	en
heal.journalName	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics	en
dc.identifier.doi	10.1109/ICSMC.1993.390760	en
dc.identifier.volume	4	en
dc.identifier.spage	485	en
dc.identifier.epage	490	en