USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS

Full metadata record

DC Field	Value	Language
dc.contributor.author	CHIANG, CC	en_US
dc.contributor.author	FU, HC	en_US
dc.date.accessioned	2014-12-08T15:04:00Z	-
dc.date.available	2014-12-08T15:04:00Z	-
dc.date.issued	1994-05-01	en_US
dc.identifier.issn	1045-9227	en_US
dc.identifier.uri	http://dx.doi.org/10.1109/72.286930	en_US
dc.identifier.uri	http://hdl.handle.net/11536/2498	-
dc.description.abstract	This 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.iso	en_US	en_US
dc.title	USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS	en_US
dc.type	Letter	en_US
dc.identifier.doi	10.1109/72.286930	en_US
dc.identifier.journal	IEEE TRANSACTIONS ON NEURAL NETWORKS	en_US
dc.citation.volume	5	en_US
dc.citation.issue	3	en_US
dc.citation.spage	516	en_US
dc.citation.epage	519	en_US
dc.contributor.department	資訊工程學系	zh_TW
dc.contributor.department	Department of Computer Science	en_US
dc.identifier.wosnumber	WOS:A1994NR36000024	-
dc.citation.woscount	4	-
Appears in Collections:	Articles

Files in This Item:

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.