DC Field | Value | Language |
---|---|---|
dc.contributor.author | CHO, SB | ko |
dc.contributor.author | Kim, JinHyung | ko |
dc.date.accessioned | 2009-11-05T02:01:41Z | - |
dc.date.available | 2009-11-05T02:01:41Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 1995-03 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON NEURAL NETWORKS, v.6, no.2, pp.497 - 501 | - |
dc.identifier.issn | 1045-9227 | - |
dc.identifier.uri | http://hdl.handle.net/10203/12141 | - |
dc.description.abstract | Multiplayer feedforward networks trained by minimizing the mean squared error and by using a one of c teaching function yield network outputs that estimate posterior class probabilities. This provides a sound basis for combining the results from multiple networks to get more accurate classification. This paper presents a method for combining multiple networks based on fuzzy logic, especially the fuzzy integral. This method non-linearly combines objective evidence, in the form of a network output, with subjective evaluation of the importance of the individual neural networks. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly. | - |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | MULTIPLE NETWORK FUSION USING FUZZY-LOGIC | - |
dc.type | Article | - |
dc.identifier.wosid | A1995QJ92200020 | - |
dc.identifier.scopusid | 2-s2.0-0029264250 | - |
dc.type.rims | ART | - |
dc.citation.volume | 6 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 497 | - |
dc.citation.endingpage | 501 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON NEURAL NETWORKS | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kim, JinHyung | - |
dc.contributor.nonIdAuthor | CHO, SB | - |
dc.type.journalArticle | Letter | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.