Adaptive training of multilayer neural networks using a least squares estimation technique

Kollias, S; Anastassiou, D

dc.contributor.author	Kollias, S	en
dc.contributor.author	Anastassiou, D	en
dc.date.accessioned	2014-03-01T02:47:49Z
dc.date.available	2014-03-01T02:47:49Z
dc.date.issued	1988	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33375
dc.subject	Artificial Neural Network	en
dc.subject	backpropagation	en
dc.subject	Computational Complexity	en
dc.subject	Convergence Rate	en
dc.subject	Least Square Method	en
dc.subject	Least Squares Estimate	en
dc.subject	Local Minima	en
dc.subject	Multilayer Neural Network	en
dc.subject	Optimization Technique	en
dc.title	Adaptive training of multilayer neural networks using a least squares estimation technique	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICNN.1988.23870	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICNN.1988.23870	en
heal.publicationDate	1988	en
heal.abstract	A technique is developed for the training of artificial neural networks, using a modification of the Marquardt-Levenberg optimization technique. An adaptive choice of the convergence rate factor μ, based on the contribution of each neuron in the minimization of the error function, is presented that can be very useful in handling the problem of local minima of the error function.	en
heal.journalName	International Symposium on Neural Networks	en
dc.identifier.doi	10.1109/ICNN.1988.23870	en