Training neural networks and neuro-fuzzy systems: a unified view

Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.1/2313

Título:	Training neural networks and neuro-fuzzy systems: a unified view
Autor:	Ruano, A. E. Ferreira, P. M. Cabrita, Cristiano Lourenço Matos, S.
Palavras-chave:	Neural Networks Neuro-Fuzzy Systems Multilayer Perceptrons Radial Basis Functions Wavelet Neural Networks
Data:	2002
Editora:	IFAC, Elsevier
Citação:	Ruano, A. E.; Ferreira, P.M.; Cabrita, C.; Matos, S. Training neural networks and neuro-fuzzy systems: A unified view, Trabalho apresentado em World Congress, In Proceedings of the 15th IFAC World Congress, 2002, Barcelona, 2002.
Resumo:	Neural and neuro-fuzzy models are powerful nonlinear modelling tools. Different structures, with different properties, are widely used to capture static or dynamical nonlinear mappings. Static (non-recurrent) models share a common structure: a nonlinear stage, followed by a linear mapping. In this paper, the separability of linear and nonlinear parameters is exploited for completely supervised training algorithms. Examples of this unified view are presented, involving multilayer perceptrons, radial basis functions, wavelet networks, B-splines, Mamdani and TSK fuzzy systems.
Peer review:	yes
URI:	http://hdl.handle.net/10400.1/2313
ISBN:	9783902661746
Aparece nas colecções:	FCT2-Artigos (em revistas ou actas indexadas)

Ficheiros deste registo:

Ficheiro	Descrição	Tamanho	Formato
2795.pdf		113,58 kB	Adobe PDF	Ver/Abrir Acesso Restrito. Solicitar cópia ao autor!