Global minimization of a quadratic functional: neural network approach

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

The problem of finding out the global minimum of a multiextremal functional is discussed. One frequently faces with such a functional in various applications. We propose a procedure, which depends on the dimensionality of the problem polynomially. In our approach we use the eigenvalues and eigenvectors of the connection matrix.
4 pages, Lecture on 7th International Conference on Pattern Recognition and Image Analysis PRIA-07-2004, St. Petersburg, Russia

Keywords

Neural and Evolutionary Computing, Discrete Mathematics

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/32542

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cs/0412109
 http://arxiv.org/abs/cs/0412109

Collections

arXiv