Radial basis function networks with quantized parameters

dc.contributorUniversidade Estadual Paulista (Unesp)
dc.date.accessioned2014-05-27T11:23:40Z
dc.date.accessioned2022-10-05T18:13:30Z
dc.date.available2014-05-27T11:23:40Z
dc.date.available2022-10-05T18:13:30Z
dc.date.created2014-05-27T11:23:40Z
dc.date.issued2008-09-30
dc.identifierCIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings, p. 23-27.
dc.identifierhttp://hdl.handle.net/11449/70591
dc.identifier10.1109/CIMSA.2008.4595826
dc.identifierWOS:000259443400006
dc.identifier2-s2.0-52449111383
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/3919871
dc.description.abstractA RBFN implemented with quantized parameters is proposed and the relative or limited approximation property is presented. Simulation results for sinusoidal function approximation with various quantization levels are shown. The results indicate that the network presents good approximation capability even with severe quantization. The parameter quantization decreases the memory size and circuit complexity required to store the network parameters leading to compact mixed-signal circuits proper for low-power applications. ©2008 IEEE.
dc.languageeng
dc.relationCIMSA 2008 - IEEE Conference on Computational Intelligence for Measurement Systems and Applications Proceedings
dc.rightsAcesso aberto
dc.sourceScopus
dc.subjectFunction approximation
dc.subjectQuantized parameters
dc.subjectRadial basis function network
dc.subjectArtificial intelligence
dc.subjectChlorine compounds
dc.subjectFeedforward neural networks
dc.subjectIntelligent control
dc.subjectNetworks (circuits)
dc.subjectPolynomial approximation
dc.subjectApproximation properties
dc.subjectCircuit complexity
dc.subjectComputational intelligence
dc.subjectInternational conferences
dc.subjectLow-power applications
dc.subjectMeasurement systems
dc.subjectMemory size
dc.subjectMixed-signal circuits
dc.subjectNetwork parameters
dc.subjectQuantization levels
dc.subjectSimulation results
dc.subjectSinusoidal functions
dc.subjectRadial basis function networks
dc.titleRadial basis function networks with quantized parameters
dc.typeTrabalho apresentado em evento


Este ítem pertenece a la siguiente institución