Multidimensional Polynomial Powers of Sigmoid (PPS) wavelet neural networks

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorLisbon University-
Autor(es): dc.creatorMarar, João Fernando-
Autor(es): dc.creatorCoelho, Helder-
Data de aceite: dc.date.accessioned2025-08-21T21:45:07Z-
Data de disponibilização: dc.date.available2025-08-21T21:45:07Z-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2008-11-13-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/225323-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/225323-
Descrição: dc.descriptionWavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.-
Descrição: dc.descriptionDepartment of Computing Faculdade de Ciências São Paulo State University, Bauru, São Paulo-
Descrição: dc.descriptionDepartment of Informatics Faculdade de Ciências Lisbon University, Lisbon-
Descrição: dc.descriptionDepartment of Computing Faculdade de Ciências São Paulo State University, Bauru, São Paulo-
Formato: dc.format261-268-
Idioma: dc.languageen-
Relação: dc.relationBIOSIGNALS 2008 - Proceedings of the 1st International Conference on Bio-inspired Systems and Signal Processing-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectActivation functions-
Palavras-chave: dc.subjectArtificial neural network-
Palavras-chave: dc.subjectFeedforward networks-
Palavras-chave: dc.subjectFunction approximation-
Palavras-chave: dc.subjectPolynomial Powers of Sigmoid (PPS)-
Palavras-chave: dc.subjectPPS-wavelet neural networks-
Palavras-chave: dc.subjectWavelets functions-
Título: dc.titleMultidimensional Polynomial Powers of Sigmoid (PPS) wavelet neural networks-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.