Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Neural networks for variational problems in engineering

Autor
López, R.; Balsa-Canto, E.; Oñate, E.
Tipus d'activitat
Article en revista
Revista
International journal for numerical methods in engineering
Data de publicació
2008-09
Volum
75
Número
11
Pàgina inicial
1341
Pàgina final
1360
DOI
https://doi.org/10.1002/nme.2304 Obrir en finestra nova
Repositori
https://www.researchgate.net/publication/229872958_Neural_Networks_for_Variational_Problems_in_Engineering Obrir en finestra nova
URL
https://onlinelibrary.wiley.com/doi/abs/10.1002/nme.2304 Obrir en finestra nova
Resum
In 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 particula...
Paraules clau
Functional analysis, Inverse problems, Multilayer perceptron, Neural networks, Optimal control, Shape design, Variational calculus
Grup de recerca
(MC)2 - UPC Mecànica de Medis Continus i Computacional
GMNE - Grup de Mètodes Numèrics en Enginyeria

Participants