Full metadata record
DC FieldValueLanguage
dc.contributor.authorCHIANG, CCen_US
dc.contributor.authorFU, HCen_US
dc.date.accessioned2014-12-08T15:04:00Z-
dc.date.available2014-12-08T15:04:00Z-
dc.date.issued1994-05-01en_US
dc.identifier.issn1045-9227en_US
dc.identifier.urihttp://dx.doi.org/10.1109/72.286930en_US
dc.identifier.urihttp://hdl.handle.net/11536/2498-
dc.description.abstractThis letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of muitilayer neural networks. In cooperation with single-threshold quadratic sigmoidal neurons, the multithreshold quadratic sigmoidal neurons can be used to improve the classification capability of multilayer neural networks by a factor of four compared to committee machines and by a factor of two compared to the conventional sigmoidal multilayer perceptrons.en_US
dc.language.isoen_USen_US
dc.titleUSING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONSen_US
dc.typeLetteren_US
dc.identifier.doi10.1109/72.286930en_US
dc.identifier.journalIEEE TRANSACTIONS ON NEURAL NETWORKSen_US
dc.citation.volume5en_US
dc.citation.issue3en_US
dc.citation.spage516en_US
dc.citation.epage519en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:A1994NR36000024-
dc.citation.woscount4-
Appears in Collections:Articles


Files in This Item:

  1. A1994NR36000024.pdf