Show simple item record

dc.contributor.authorPinter, Janos D.
dc.date.accessioned2016-08-18T08:56:33Z
dc.date.available2016-08-18T08:56:33Z
dc.date.issued2012-01
dc.identifier.issn0957-4174en_US
dc.identifier.urihttp://hdl.handle.net/10679/4441
dc.identifier.urihttp://www.sciencedirect.com/science/article/pii/S095741741100950X
dc.descriptionDue to copyright restrictions, the access to the full text of this article is only available via subscription.
dc.description.abstractArtificial neural networks (ANNs) are used extensively to model unknown or unspecified functional relationships between the input and output of a “black box” system. In order to apply the generic ANN concept to actual system model fitting problems, a key requirement is the training of the chosen (postulated) ANN structure. Such training serves to select the ANN parameters in order to minimize the discrepancy between modeled system output and the training set of observations. We consider the parameterization of ANNs as a potentially multi-modal optimization problem, and then introduce a corresponding global optimization (GO) framework. The practical viability of the GO based ANN training approach is illustrated by finding close numerical approximations of one-dimensional, yet visibly challenging functions. For this purpose, we have implemented a flexible ANN framework and an easily expandable set of test functions in the technical computing system Mathematica. The MathOptimizer Professional global–local optimization software has been used to solve the induced (multi-dimensional) ANN calibration problems.en_US
dc.description.sponsorshipÖzyeğin University ; Simulation and Optimization Project of Széchenyi István University
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.ispartofExpert Systems with Applicationsen_US
dc.rightsrestrictedAccess
dc.titleCalibrating artificial neural networks by global optimizationen_US
dc.typeArticleen_US
dc.peerreviewedyesen_US
dc.publicationstatuspublisheden_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID(ORCID & YÖK ID 202094) Pinter, Janos
dc.contributor.ozuauthorPinter, Janos D.
dc.identifier.volume39en_US
dc.identifier.issue1en_US
dc.identifier.startpage25en_US
dc.identifier.endpage32en_US
dc.identifier.wosWOS:000296214900004
dc.identifier.doi10.1016/j.eswa.2011.06.050en_US
dc.subject.keywordsArtificial neural networksen_US
dc.subject.keywordsCalibration of ANNs by global optimizationen_US
dc.subject.keywordsANN implementation in Mathematicaen_US
dc.subject.keywordsLipschitz Global Optimizer (LGO) solver suiteen_US
dc.subject.keywordsMathOptimizer Professional (LGO linked to Mathematica)en_US
dc.subject.keywordsNumerical examplesen_US
dc.identifier.scopusSCOPUS:2-s2.0-81855207560
dc.contributor.authorMale1
dc.relation.publicationcategoryArticle - International Refereed Journal - Institutional Academic Staff


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


Share this page