DC Field | Value | Language |
---|---|---|
dc.contributor.author | cho, Jae-Soo | ko |
dc.contributor.author | Kim, Yong-Woon | ko |
dc.contributor.author | Park, Dong-Jo | ko |
dc.date.accessioned | 2013-02-27T18:10:00Z | - |
dc.date.available | 2013-02-27T18:10:00Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 1997-12 | - |
dc.identifier.citation | ELECTRONICS LETTERS, v.33, no.25, pp.2133 - 2135 | - |
dc.identifier.issn | 0013-5194 | - |
dc.identifier.uri | http://hdl.handle.net/10203/70016 | - |
dc.description.abstract | A new neural network architecture, called a higher order diagonal recurrent neural network (HDRNN), is presented. The architecture of an HDRNN is a modified model of the diagonal recurrent neural network (DRNN) with one hidden layer which is composed of self-recurrent neurons and additional multiplication inputs between conventional inputs and self-recurrent neurons. The authors derive a generalised dynamic backpropagation algorithm and show that the proposed HDRNN not only gives more accurate identification results, but also requires a shorter training time to obtain the desired accuracy. | - |
dc.language | English | - |
dc.publisher | IEE-INST ELEC ENG | - |
dc.title | Identification of nonlinear dynamic systems using higher order diagonal recurrent neural network | - |
dc.type | Article | - |
dc.identifier.wosid | 000072041800036 | - |
dc.identifier.scopusid | 2-s2.0-0031553142 | - |
dc.type.rims | ART | - |
dc.citation.volume | 33 | - |
dc.citation.issue | 25 | - |
dc.citation.beginningpage | 2133 | - |
dc.citation.endingpage | 2135 | - |
dc.citation.publicationname | ELECTRONICS LETTERS | - |
dc.contributor.localauthor | Park, Dong-Jo | - |
dc.contributor.nonIdAuthor | cho, Jae-Soo | - |
dc.contributor.nonIdAuthor | Kim, Yong-Woon | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | recurrent neural nets | - |
dc.subject.keywordAuthor | nonlinear dynamic systems | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.