Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm

dc.creatorSussner, P
dc.creatorEsmi, EL
dc.date2011
dc.dateMAY 15
dc.date2014-08-01T18:41:50Z
dc.date2015-11-26T16:28:45Z
dc.date2014-08-01T18:41:50Z
dc.date2015-11-26T16:28:45Z
dc.date.accessioned2018-03-28T23:09:48Z
dc.date.available2018-03-28T23:09:48Z
dc.identifierInformation Sciences. Elsevier Science Inc, v. 181, n. 10, n. 1929, n. 1950, 2011.
dc.identifier0020-0255
dc.identifierWOS:000288833300011
dc.identifier10.1016/j.ins.2010.03.016
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/82220
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/82220
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1269553
dc.descriptionA morphological neural network is generally defined as a type of artificial neural network that performs an elementary operation of mathematical morphology at every node, possibly followed by the application of an activation function. The underlying framework of mathematical morphology can be found in lattice theory. With the advent of granular computing, lattice-based neurocomputing models such as morphological neural networks and fuzzy lattice neurocomputing models are becoming increasingly important since many information granules such as fuzzy sets and their extensions, intervals, and rough sets are lattice ordered. In this paper, we present the lattice-theoretical background and the learning algorithms for morphological perceptrons with competitive learning which arise by incorporating a winner-take-all output layer into the original morphological perceptron model. Several well-known classification problems that are available on the internet are used to compare our new model with a range of classifiers such as conventional multi-layer perceptrons, fuzzy lattice neurocomputing models, k-nearest neighbors, and decision trees. (C) 2010 Elsevier Inc. All rights reserved.
dc.description181
dc.description10
dc.descriptionSI
dc.description1929
dc.description1950
dc.languageen
dc.publisherElsevier Science Inc
dc.publisherNew York
dc.publisherEUA
dc.relationInformation Sciences
dc.relationInf. Sci.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectComputational intelligence
dc.subjectLattice theory
dc.subjectMathematical morphology
dc.subjectMinimax algebra
dc.subjectMorphological neural network
dc.subjectMorphological perceptron
dc.subjectCompetitive neuron
dc.subjectPattern recognition
dc.subjectClassification
dc.subjectWeight Neural-networks
dc.subjectFuzzy Mathematical Morphologies
dc.subjectAssociative Memories
dc.subjectGray-scale
dc.subjectReasoning Flr
dc.subjectSet-theory
dc.subjectClassification
dc.titleMorphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución