English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/55232
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

Title

Neural networks for variational problems in engineering

AuthorsLópez, R.; Balsa-Canto, Eva ; Oñate, Eugenio
KeywordsNeural network
Multilayer perceptron
Functional analysis
Variational calculus
Shape design
Optimal control
Inverse problems
Issue Date2008
PublisherJohn Wiley & Sons
CitationInternational Journal for Numerical Methods in Engineering 75(11): 1341-1360 (2008)
AbstractIn this work a conceptual theory of neural networks (NNs) from the perspective of functional analysis and variational calculus is presented. Within this formulation, the learning problem for the multilayer perceptron lies in terms of finding a function, which is an extremal for some functional. Therefore, a variational formulation for NNs provides a direct method for the solution of variational problems. This proposed method is then applied to distinct types of engineering problems. In particular a shape design, an optimal control and an inverse problem are considered. The selected examples can be solved analytically, which enables a fair comparison with the NN results
Description20 páginas, 12 figuras, 3 tablas
Publisher version (URL)http://dx.doi.org/10.1002/nme.2304
URIhttp://hdl.handle.net/10261/55232
DOIhttp://dx.doi.org/10.1002/nme.2304
ISSN0029-5981
E-ISSN1097-0207
Appears in Collections:(IIM) Artículos
Files in This Item:
There are no files associated with this item.
Show full item record
Review this work
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.