Comparative study between powers of sigmoid functions, MLP-backpropagation and polynomials in function approximation problems

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorMarar, João Fernando
dc.creatorPatrocinio, Ana Claudia
dc.date2014-05-27T11:19:41Z
dc.date2016-10-25T21:21:51Z
dc.date2014-05-27T11:19:41Z
dc.date2016-10-25T21:21:51Z
dc.date1999-01-01
dc.date.accessioned2017-04-06T09:24:20Z
dc.date.available2017-04-06T09:24:20Z
dc.identifierSignal Processing, Sensor Fusion, and Target Recognition Viii. Bellingham: Spie-int Soc Optical Engineering, v. 3720, p. 451-458, 1999.
dc.identifier0277-786X
dc.identifierhttp://hdl.handle.net/11449/130718
dc.identifierhttp://acervodigital.unesp.br/handle/11449/130718
dc.identifier10.1117/12.357191
dc.identifierWOS:000082902100045
dc.identifier2-s2.0-0032683364
dc.identifierhttp://dx.doi.org/10.1117/12.357191
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/941260
dc.descriptionFunction approximation is a very important task in environments where the computation has to be based on extracting information from data samples in real world processes. So, the development of new mathematical model is a very important activity to guarantee the evolution of the function approximation area. In this sense, we will present the Polynomials Powers of Sigmoid (PPS) as a linear neural network. In this paper, we will introduce one series of practical results for the Polynomials Powers of Sigmoid, where we will show some advantages of the use of the powers of sigmiod functions in relationship the traditional MLP-Backpropagation and Polynomials in functions approximation problems.
dc.languageeng
dc.publisherSpie - Int Soc Optical Engineering
dc.relationProceedings of SPIE - The International Society for Optical Engineering
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectApproximation theory
dc.subjectBackpropagation
dc.subjectFunction evaluation
dc.subjectPolynomials
dc.subjectFunction approximation
dc.subjectPolynomials powers of sigmoid (PPS)
dc.subjectMultilayer neural networks
dc.titleComparative study between powers of sigmoid functions, MLP-backpropagation and polynomials in function approximation problems
dc.typeOtro


Este ítem pertenece a la siguiente institución