Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/342456
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.contributor.authorunicampSussner, Peter-
dc.typeArtigopt_BR
dc.titleExtreme learning machine for a new hybrid morphological/linear perceptronpt_BR
dc.contributor.authorSussner, P.-
dc.contributor.authorCampiotti, I.-
dc.subjectAprendizado de máquinapt_BR
dc.subjectProgramação não-linearpt_BR
dc.subjectRedes neurais (Computação)pt_BR
dc.subjectMemória associativapt_BR
dc.subject.otherlanguageMachine learningpt_BR
dc.subject.otherlanguageNonlinear programmingpt_BR
dc.subject.otherlanguageNeural networks (Computer science)pt_BR
dc.subject.otherlanguageAssociative memorypt_BR
dc.description.abstractMorphological neural networks (MNNs) can be characterized as a class of artificial neural networks that perform an operation of mathematical morphology at every node, possibly followed by the application of an activation function. Morphological perceptrons (MPs) and (gray-scale) morphological associative memories are among the most widely known MNN models. Since their neuronal aggregation functions are not differentiable, classical methods of non-linear optimization can in principle not be directly applied in order to train these networks. The same observation holds true for hybrid morphological/linear perceptrons and other related models. Circumventing these problems of non-differentiability, this paper introduces an extreme learning machine approach for training a hybrid morphological/linear perceptron, whose morphological components were drawn from previous MP models. We apply the resulting model to a number of well-known classification problems from the literature and compare the performance of our model with the ones of several related models, including some recent MNNs and hybrid morphological/linear neural networkspt_BR
dc.relation.ispartofNeural networkspt_BR
dc.relation.ispartofabbreviationNeural netw.pt_BR
dc.publisher.cityOxfordpt_BR
dc.publisher.countryReino Unidopt_BR
dc.publisherElsevierpt_BR
dc.date.issued2020-
dc.date.monthofcirculationMar.pt_BR
dc.language.isoengpt_BR
dc.description.volume123pt_BR
dc.description.firstpage288pt_BR
dc.description.lastpage298pt_BR
dc.rightsFechadopt_BR
dc.sourceSCOPUSpt_BR
dc.identifier.issn0893-6080pt_BR
dc.identifier.eissn1879-2782pt_BR
dc.identifier.doi10.1016/j.neunet.2019.12.003pt_BR
dc.identifier.urlhttps://www.sciencedirect.com/science/article/pii/S0893608019303958pt_BR
dc.date.available2020-06-02T16:30:04Z-
dc.date.accessioned2020-06-02T16:30:04Z-
dc.description.provenanceSubmitted by Cintia Oliveira de Moura (cintiaom@unicamp.br) on 2020-06-02T16:30:04Z No. of bitstreams: 0. Added 1 bitstream(s) on 2020-09-03T11:55:27Z : No. of bitstreams: 1 2-s2.0-85076963298.pdf: 1078773 bytes, checksum: 39394bca1fb896bf1455323b70bc8987 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-06-02T16:30:04Z (GMT). No. of bitstreams: 0 Previous issue date: 2020en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/342456-
dc.contributor.departmentDepartamento de Matemática Aplicadapt_BR
dc.contributor.unidadeInstituto de Matemática, Estatística e Computação Científicapt_BR
dc.subject.keywordMachine componentspt_BR
dc.subject.keywordMathematical morphologypt_BR
dc.identifier.source2-s2.0-85076963298pt_BR
dc.creator.orcid0000-0002-8457-7127pt_BR
dc.type.formArtigopt_BR
Appears in Collections:IMECC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-85076963298.pdf1.05 MBAdobe PDFView/Open


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