Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.1/87
Título: A hybrid training method for B-spline neural networks
Autor: Cabrita, Cristiano Lourenço
Botzheim, J.
Ruano, A. E.
Kóczy, László T.
Palavras-chave: Algoritmo de levenberg-marquard
Algoritmo bacteriano
Programação genética
B-splines
Data: 2008
Editora: Faro
Citação: IEEE International Workshop on Intelligent Signal Processing (WISP). - Faro, 1-3 September 2005. - p. 165-170
Resumo: Current and past research has brought up new views related to the optimization of neural networks. For a fixed structure, second order methods are seen as the most promising. From previous works we have shown how second order methods are of easy applicability to a neural network. Namely, we have proved how the Levenberg-Marquard possesses not only better convergence but how it can assure the convergence to a local minima. However, as any gradient-based method, the results obtained depend on the startup point. In this work, a reformulated Evolutionary algorithm - the Bacterial Programming for Levenberg-Marquardt is proposed, as an heuristic which can be used to determine the most suitable starting points, therefore achieving, in most cases, the global optimum.
URI: http://hdl.handle.net/10400.1/87
Aparece nas colecções:ISE3-Livros (ou partes, com ou sem arbitragem científica)

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
CABHyb.pdf434,36 kBAdobe PDFVer/Abrir    Acesso Restrito. Solicitar cópia ao autor!


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.