Optimizing feedforward artificial neural network architecture

Benardos, PG; Vosniakos, GC

dc.contributor.author	Benardos, PG	en
dc.contributor.author	Vosniakos, GC	en
dc.date.accessioned	2014-03-01T01:26:50Z
dc.date.available	2014-03-01T01:26:50Z
dc.date.issued	2007	en
dc.identifier.issn	0952-1976	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/18248
dc.subject	feedforward artificial neural networks	en
dc.subject	ANN architecture	en
dc.subject	generalization	en
dc.subject	genetic algorithms	en
dc.subject	engineering problems	en
dc.subject.classification	Automation & Control Systems	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Engineering, Multidisciplinary	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	GENETIC ALGORITHMS	en
dc.subject.other	PERFORMANCE	en
dc.subject.other	DESIGN	en
dc.subject.other	SYSTEM	en
dc.title	Optimizing feedforward artificial neural network architecture	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.engappai.2006.06.005	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.engappai.2006.06.005	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	Despite the fact that feedforward artificial neural networks (ANNs) have been a hot topic of research for many years there still are certain issues regarding the development of an ANN model, resulting in a lack of absolute guarantee that the model will perform well for the problem at hand. The multitude of different approaches that have been adopted in order to deal with this problem have investigated all aspects of the ANN modelling procedure, from training data collection and pre/post-processing to elaborate training schemes and algorithms. Increased attention is especially directed to proposing a systematic way to establish an appropriate architecture in contrast to the current common practice that calls for a repetitive trial-and-error process, which is time-consuming and produces uncertain results. This paper proposes such a methodology for determining the best architecture and is based on the use of a genetic algorithm (GA) and the development of novel criteria that quantify an ANN's performance (both training and generalization) as well as its complexity. This approach is implemented in software and tested based on experimental data capturing workpiece elastic deflection in turning. The intention is to present simultaneously the approach's theoretical background and its practical application in real-life engineering problems. Results show that the approach performs better than a human expert, at the same time offering many advantages in comparison to similar approaches found in literature. (c) 2006 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE	en
dc.identifier.doi	10.1016/j.engappai.2006.06.005	en
dc.identifier.isi	ISI:000245477700006	en
dc.identifier.volume	20	en
dc.identifier.issue	3	en
dc.identifier.spage	365	en
dc.identifier.epage	382	en