Please use this identifier to cite or link to this item:

TitleSimultaneous evolution of neural network topologies and weights for classification and regression
Author(s)Rocha, Miguel
Cortez, Paulo
Neves, José
KeywordsSupervised learning
Multilayer perceptrons
Evolutionary algorithms
Issue date8-Jun-2005
JournalLecture Notes in Computer Science
CitationINTERNATIONAL WORK-CONFERENCE ON ARTIFICIAL NEURAL NETWORKS (IWANN), 8, Barcelona, 2005 - "Computational intelligence and bioinspired systems : proceedings". Heidelberg : Springer, 2005. ISBN 3-540-26208-3. p. 59-66.
Abstract(s)Artificial Neural Networks (ANNs) are important Data Mining (DM) techniques. Yet, the search for the optimal ANN is a challenging task: the architecture should learn the input-output mapping without overfitting the data and training algorithms tend to get trapped into local minima. Under this scenario, the use of Evolutionary Computation (EC) is a promising alternative for ANN design and training. Moreover, since EC methods keep a pool of solutions, an ensemble can be build by combining the best ANNs. This work presents a novel algorithm for the optimization of ANNs, using a direct representation, a structural mutation operator and Lamarckian evolution. Sixteen real-world classification/regression tasks were used to test this strategy with single and ensemble based versions. Competitive results were achieved when compared with a heuristic model selection and other DM algorithms.
Publisher versionThe original publication is available at
Appears in Collections:DSI - Engenharia da Programação e dos Sistemas Informáticos
DI/CCTC - Artigos (papers)
CAlg - Artigos em livros de atas/Papers in proceedings

Files in This Item:
File Description SizeFormat 
spr-59.pdf201,85 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis