Please use this identifier to cite or link to this item: http://repositoriosenaiba.fieb.org.br/handle/fieb/299
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMonteiro, Roberto L. S.-
dc.contributor.authorCarneiro, Tereza Kelly G.-
dc.contributor.authorFontoura, José Roberto A.-
dc.contributor.authorSilva, Valéria L. da-
dc.date.accessioned2016-07-07T16:25:14Z-
dc.date.issued2016-02-22-
dc.identifier.citationMONTEIRO, Roberto L. S. et al. A Model for Improving the Learning Curves of Artificial Neural Networks. Plos One , v. 11, p. e0149874, 2016.pt_BR
dc.identifier.urihttp://repositoriosenaiba.fieb.org.br/handle/fieb/299-
dc.descriptionp.1-11pt_BR
dc.description.abstractIn this article, the performance of a hybrid artificial neural network (i.e. scale-free and smallworld) was analyzed and its learning curve compared to three other topologies: random, scale-free and small-world, as well as to the chemotaxis neural network of the nematode Caenorhabditis Elegans. One hundred equivalent networks (same number of vertices and average degree) for each topology were generated and each was trained for one thousand epochs. After comparing the mean learning curves of each network topology with the C. elegans neural network, we found that the networks that exhibited preferential attachment exhibited the best learning curves.pt_BR
dc.language.isoen_USpt_BR
dc.sourcehttp://journals.plos.org/plosone/article/asset?id=10.1371%2Fjournal.pone.0149874.PDFpt_BR
dc.subjectNeural network - Performancept_BR
dc.subjectArtificial neural networkpt_BR
dc.subjectNeural network - learning curvept_BR
dc.titleA Model for improving the learning curves of artificial neural networkspt_BR
dc.title.alternativePlos Onept_BR
dc.typeProdução bibliográfica: Artigos completos publicados em periódicospt_BR
dc.embargo.termsabertopt_BR
dc.embargo.lift2016-07-08T16:25:14Z-
Appears in Collections:Artigos Publicados em Periódicos (PPG MCTI)

Files in This Item:
File Description SizeFormat 
A model for improving ....PDF1.27 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.