dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorda Silva, I. N.
dc.creatorAmaral, W. C.
dc.creatorArruda, L. V. R.
dc.date2014-05-20T15:28:36Z
dc.date2016-10-25T18:03:42Z
dc.date2014-05-20T15:28:36Z
dc.date2016-10-25T18:03:42Z
dc.date2006-03-01
dc.date.accessioned2017-04-06T00:08:01Z
dc.date.available2017-04-06T00:08:01Z
dc.identifierJournal of Optimization Theory and Applications. New York: Springer/plenum Publishers, v. 128, n. 3, p. 563-580, 2006.
dc.identifier0022-3239
dc.identifierhttp://hdl.handle.net/11449/38376
dc.identifierhttp://acervodigital.unesp.br/handle/11449/38376
dc.identifier10.1007/s10957-006-9032-9
dc.identifierWOS:000241554100005
dc.identifierhttp://dx.doi.org/10.1007/s10957-006-9032-9
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/881503
dc.descriptionNeural networks consist of highly interconnected and parallel nonlinear processing elements that are shown to be extremely effective in computation. This paper presents an architecture of recurrent neural net-works that can be used to solve several classes of optimization problems. More specifically, a modified Hopfield network is developed and its inter-nal parameters are computed explicitly using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent a solution of the problem considered. The problems that can be treated by the proposed approach include combinatorial optimiza-tion problems, dynamic programming problems, and nonlinear optimization problems.
dc.languageeng
dc.publisherSpringer
dc.relationJournal of Optimization Theory and Applications
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectrecurrent neural networks
dc.subjectnonlinear optimization
dc.subjectdynamic programming
dc.subjectcombinatorial optimization
dc.subjectHopfield network
dc.titleNeural approach for solving several types of optimization problems
dc.typeOtro


Este ítem pertenece a la siguiente institución