MULTIOBJECTIVE EVOLUTIONARY OPTIMIZATION FOR ELMAN RECURRENT NEURAL NETWORKS, APPLIED TO TIME SERIES PREDICTION

M. P. Cuellar, M. Delgado and M. C. Pegalajar
Additional contact information
M. C. Pegalajar: University of Granada

Fuzzy Economic Review, 2005, vol. X, issue 1, 17-33

Abstract: In previous works, we showed how Recurrent Neural Networks, trained with Genetic Algorithms, can achieve a good performance in Time Series Pre-diction problems. However, the problem of finding the optimal structure of the Network is still a tedious task, which requires several experiments and multiple tests. In this work, we propose a Multiobjective Evolutionary Algorithm to find the optimal topology of the Network. The algorithm also provides a set of optimal networks trained. In the experimental section, we apply the algorithm to obtain optimal Elman Recurrent Neural Networks, in order to predict the evolution of the population of the U.S. and the ECB reference exchange rate between the US dollar and the euro, between others time series

Keywords: Recurrent Neural Networks; multiobjective; time series prediction (search for similar items in EconPapers)
JEL-codes: C45 (search for similar items in EconPapers)
Date: 2005
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:fzy:fuzeco:v:x:y:2005:i:1:p:17-33

Access Statistics for this article

More articles in Fuzzy Economic Review from International Association for Fuzzy-set Management and Economy (SIGEF) Contact information at EDIRC.
Bibliographic data for series maintained by Aurelio Fernandez ( this e-mail address is bad, please contact ).