Morphological bidirectional associative memories

dc.creatorRitter, GX
dc.creatorDiaz-De-Leon, JL
dc.creatorSussner, P
dc.date1999
dc.dateJUL
dc.date2014-12-02T16:26:33Z
dc.date2015-11-26T17:54:01Z
dc.date2014-12-02T16:26:33Z
dc.date2015-11-26T17:54:01Z
dc.date.accessioned2018-03-29T00:37:39Z
dc.date.available2018-03-29T00:37:39Z
dc.identifierNeural Networks. Pergamon-elsevier Science Ltd, v. 12, n. 6, n. 851, n. 867, 1999.
dc.identifier0893-6080
dc.identifierWOS:000082104300006
dc.identifier10.1016/S0893-6080(99)00033-7
dc.identifierhttp://www.repositorio.unicamp.br/jspui/handle/REPOSIP/82201
dc.identifierhttp://www.repositorio.unicamp.br/handle/REPOSIP/82201
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/82201
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1290686
dc.descriptionThe theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we discuss a novel class of artificial neural networks, called morphological neural networks ;s in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different from those of traditional neural network models. The main emphasis of the research presented here is on morphological bidirectional associative memories (MBAMs). In particular, we establish a mathematical theory for MBAMs and provide conditions that guarantee perfect bidirectional recall for corrupted patterns. Some examples that illustrate performance differences between the morphological model and the traditional semilinear model are also given. (C) 1999 Elsevier Science Ltd. All rights reserved.
dc.description12
dc.description6
dc.description851
dc.description867
dc.languageen
dc.publisherPergamon-elsevier Science Ltd
dc.publisherOxford
dc.publisherInglaterra
dc.relationNeural Networks
dc.relationNeural Netw.
dc.rightsfechado
dc.rightshttp://www.elsevier.com/about/open-access/open-access-policies/article-posting-policy
dc.sourceWeb of Science
dc.subjectassociative memories
dc.subjectbidirectional associative memories
dc.subjectmorphological neural networks
dc.subjectmorphological associative memories
dc.subjectShared-weight Networks
dc.subjectNeural Networks
dc.subjectImage Algebra
dc.titleMorphological bidirectional associative memories
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución