Design of Artificial Neural Networks using Evolutionary Computation

Francisco Sandoval (), Francisco Garcìa-Lagos () and Gonzalo Joya ()
Additional contact information
Francisco Sandoval: Universidad de Málaga
Francisco Garcìa-Lagos: Universidad de Málaga
Gonzalo Joya: Universidad de Málaga

European Journal of Economic and Social Systems, 2004, vol. 17, issue 1-2, 99-123

Abstract: Artificial Neural Networks (ANNs) offer an attractive paradigm of computation. However, it is often hard to design good ANNs because many of the basic principles governing information processing in ANNs are difficult to understand. When complex combinations of behaviour approaches are given, and the size of the nets grows in dimension and complexity, classical solutions do not work and it is necessary to appeal to more efficient automated procedures. In this intent of automated solutions the evolutionary techniques appear, being one of their main implementations the genetic algorithms, whose search strategy is based on the population. In this paper we deal with the most important characteristics of the genetic algorithms, analysing and comparing their most important constituents, and how these algorithms can be applied to the design of ANNs.

Keywords: Genetic Algorithms; Evolutionary Computation; Artificial Neural Networks (search for similar items in EconPapers)
JEL-codes: C45 (search for similar items in EconPapers)
Date: 2004
References: Add references at CitEc
Citations:

Downloads: (external link)
http://ejess.revuesonline.com/article.jsp?articleId=4500 Full text (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ris:ejessy:0133

Access Statistics for this article

European Journal of Economic and Social Systems is currently edited by Bernard Paulré and Stefano Lucarelli

More articles in European Journal of Economic and Social Systems from Lavoisier
Bibliographic data for series maintained by Stefano Lucarelli ( this e-mail address is bad, please contact ).