File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An empirical measure of element contribution in neural networks

TitleAn empirical measure of element contribution in neural networks
Authors
Issue Date1998
PublisherIEEE.
Citation
IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 1998, v. 28 n. 4, p. 561-564 How to Cite?
AbstractA frequent complaint about neural net models is that they fail to explain their results in any useful way. The problem is not a lack of information, but an abundance of information that is difficult to interpret. When trained, neural nets will provide a predicted output for a posited input, and they can provide additional information in the form of interelement connection strengths. This latter information is of little use to analysts and managers who wish to interpret the results they have been given. We develop a measure of the relative importance of the various input elements and hidden layer elements, and we use this to interpret the contribution of these components to the outputs of the neural net.
Persistent Identifierhttp://hdl.handle.net/10722/43646
ISSN
2014 Impact Factor: 6.22
2015 SCImago Journal Rankings: 3.921
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorMak, BLFen_HK
dc.contributor.authorBlanning, RWen_HK
dc.date.accessioned2007-03-23T04:51:11Z-
dc.date.available2007-03-23T04:51:11Z-
dc.date.issued1998en_HK
dc.identifier.citationIEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 1998, v. 28 n. 4, p. 561-564en_HK
dc.identifier.issn1083-4419en_HK
dc.identifier.urihttp://hdl.handle.net/10722/43646-
dc.description.abstractA frequent complaint about neural net models is that they fail to explain their results in any useful way. The problem is not a lack of information, but an abundance of information that is difficult to interpret. When trained, neural nets will provide a predicted output for a posited input, and they can provide additional information in the form of interelement connection strengths. This latter information is of little use to analysts and managers who wish to interpret the results they have been given. We develop a measure of the relative importance of the various input elements and hidden layer elements, and we use this to interpret the contribution of these components to the outputs of the neural net.en_HK
dc.format.extent101360 bytes-
dc.format.extent25088 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/msword-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.titleAn empirical measure of element contribution in neural networksen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1083-4419&volume=28&issue=4&spage=561&epage=564&date=1998&atitle=An+empirical+measure+of+element+contribution+in+neural+networksen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/5326.725342en_HK
dc.identifier.hkuros42608-
dc.identifier.isiWOS:000076590700006-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats