Feedforward neural networks based on PPS-wavelet activation functions

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorMarar, Joao Fernando-
Autor(es): dc.creatorFilho, Edson Costa B.C.-
Autor(es): dc.creatorVasconcelos, Germano Crispim-
Data de aceite: dc.date.accessioned2025-08-21T15:51:59Z-
Data de disponibilização: dc.date.available2025-08-21T15:51:59Z-
Data de envio: dc.date.issued2022-04-29-
Data de envio: dc.date.issued2022-04-29-
Data de envio: dc.date.issued1997-12-01-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/231682-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/231682-
Descrição: dc.descriptionFunction approximation is a very important task in environments where computation has to be based on extracting information from data samples in real world processes. Neural networks and wavenets have been recently seen as attractive tools for developing efficient solutions for many real world problems in function approximation. In this paper, it is shown how feedforward neural networks can be built using a different type of activation function referred to as the PPS-wavelet. An algorithm is presented to generate a family of PPS-wavelets that can be used to efficiently construct feedforward networks for function approximation.-
Descrição: dc.descriptionUNESP- Universidade Estadual Paulista, Sao Paulo-
Descrição: dc.descriptionUNESP- Universidade Estadual Paulista, Sao Paulo-
Formato: dc.format240-245-
Idioma: dc.languageen-
Relação: dc.relationProceedings of the Workshop on Cybernetic Vision-
???dc.source???: dc.sourceScopus-
Título: dc.titleFeedforward neural networks based on PPS-wavelet activation functions-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.