Optimal Genetic Representation of Complete Strictly-Layered Feedforward Neural Networks

Raptis, S; Tzafestas, S; Karagianni, H

dc.contributor.author	Raptis, S	en
dc.contributor.author	Tzafestas, S	en
dc.contributor.author	Karagianni, H	en
dc.date.accessioned	2014-03-01T02:49:05Z
dc.date.available	2014-03-01T02:49:05Z
dc.date.issued	2001	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/34288
dc.subject	Curse of Dimensionality	en
dc.subject	Genetic Algorithm	en
dc.subject	Genetics	en
dc.subject	Feedforward Neural Network	en
dc.subject	Neural Network	en
dc.title	Optimal Genetic Representation of Complete Strictly-Layered Feedforward Neural Networks	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1007/3-540-45723-2_15	en
heal.identifier.secondary	http://dx.doi.org/10.1007/3-540-45723-2_15	en
heal.publicationDate	2001	en
heal.abstract	The automatic eveolution of neural networks is both an attractive and a rewarding task. The connectivity matrix is the most common way of directly encoding a neural network for the purpose of genetic optimization. However, this representation presents several disadvantages mostly stemming from its inherent redundancy and its lack of rebustness. We propose a novel representation scheme for encoding complete	en
heal.journalName	International Work-Conference on Artificial and NaturalNeural Networks	en
dc.identifier.doi	10.1007/3-540-45723-2_15	en