Evolution of neural networks for classification and regression

dc.contributor.authorRocha, Miguel
dc.contributor.authorCortez, Paulo
dc.contributor.authorNeves, José
dc.date.accessioned2008-08-20T21:27:58Z
dc.date.available2008-08-20T21:27:58Z
dc.date.issued2007
dc.description.abstractAlthough Artificial Neural Networks (ANNs) are important Data Mining techniques, the search for the optimal ANN is a challenging task: the ANN should learn the input-output mapping without overfitting the data and training algorithms may get trapped in local minima. The use of Evolutionary Computation (EC) is a promising alternative for ANN optimization. This work presents two hybrid EC/ANN algorithms: the first evolves neural topologies while the latter performs simultaneous optimization of architectures and weights. Sixteen real-world tasks were used to test these strategies. Competitive results were achieved when compared with a heuristic model selection and other Data Mining algorithms.eng
dc.description.sponsorshipFundação para a Ciência e a Tecnologia (FCT) - projecto POSI/EIA/59899/2004.por
dc.identifier.citation"Neurocomputing". ISSN 0925-2312. 70:16-18 (Aug. 2007) 2809-2816.eng
dc.identifier.doi10.1016/j.neucom.2006.05.023por
dc.identifier.issn0925-2312
dc.identifier.urihttps://hdl.handle.net/1822/8028
dc.language.isoengeng
dc.peerreviewedyeseng
dc.publisherElseviereng
dc.relation.publisherversionhttp://www.sciencedirect.com/science/journal/09252312
dc.rightsopenAccesseng
dc.subjectSupervised learningeng
dc.subjectMultilayer perceptronseng
dc.subjectEvolutionary algorithmseng
dc.subjectLamarckian optimizationeng
dc.subjectNeural network ensembleseng
dc.subject.wosScience & Technologypor
dc.titleEvolution of neural networks for classification and regressioneng
dc.typearticleeng
dspace.entity.typePublicationen
oaire.citationEndPage2816por
oaire.citationIssue16-18por
oaire.citationStartPage2809por
oaire.citationVolume70por
sdum.journalNeurocomputingpor

Ficheiros

Pacote original

A mostrar 1 - 1 de 1
A carregar...
Nome:
enn3.pdf
Tamanho:
290.63 KB
Formato:
Adobe Portable Document Format
Descrição:
Main article (pre-print)