DC Field | Value | Language |
---|---|---|
dc.contributor.author | Khan, Shujaat | ko |
dc.contributor.author | Ahmad, Jawwad | ko |
dc.contributor.author | Naseem, Imran | ko |
dc.contributor.author | Moinuddin, Muhammad | ko |
dc.date.accessioned | 2018-02-21T05:52:37Z | - |
dc.date.available | 2018-02-21T05:52:37Z | - |
dc.date.created | 2018-02-05 | - |
dc.date.created | 2018-02-05 | - |
dc.date.issued | 2018-02 | - |
dc.identifier.citation | CIRCUITS SYSTEMS AND SIGNAL PROCESSING, v.37, no.2, pp.593 - 612 | - |
dc.identifier.issn | 0278-081X | - |
dc.identifier.uri | http://hdl.handle.net/10203/240137 | - |
dc.description.abstract | In this research, we propose a novel algorithm for learning of the recurrent neural networks called as the fractional back-propagation through time (FBPTT). Considering the potential of the fractional calculus, we propose to use the fractional calculus-based gradient descent method to derive the FBPTT algorithm. The proposed FBPTT method is shown to outperform the conventional back-propagation through time algorithm on three major problems of estimation namely nonlinear system identification, pattern classification and Mackey-Glass chaotic time series prediction. | - |
dc.language | English | - |
dc.publisher | SPRINGER BIRKHAUSER | - |
dc.subject | SYSTEMS | - |
dc.subject | BACKPROPAGATION | - |
dc.subject | CALCULUS | - |
dc.subject | TIME | - |
dc.subject | IDENTIFICATION | - |
dc.subject | PREDICTION | - |
dc.subject | MODELS | - |
dc.subject | SERIES | - |
dc.title | A Novel Fractional Gradient-Based Learning Algorithm for Recurrent Neural Networks | - |
dc.type | Article | - |
dc.identifier.wosid | 000423113900007 | - |
dc.identifier.scopusid | 2-s2.0-85040836202 | - |
dc.type.rims | ART | - |
dc.citation.volume | 37 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 593 | - |
dc.citation.endingpage | 612 | - |
dc.citation.publicationname | CIRCUITS SYSTEMS AND SIGNAL PROCESSING | - |
dc.identifier.doi | 10.1007/s00034-017-0572-z | - |
dc.contributor.localauthor | Khan, Shujaat | - |
dc.contributor.nonIdAuthor | Ahmad, Jawwad | - |
dc.contributor.nonIdAuthor | Naseem, Imran | - |
dc.contributor.nonIdAuthor | Moinuddin, Muhammad | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Back-propagation through time (BPTT) | - |
dc.subject.keywordAuthor | Recurrent neural network (RNN) | - |
dc.subject.keywordAuthor | Gradient descent | - |
dc.subject.keywordAuthor | Fractional calculus | - |
dc.subject.keywordAuthor | Mackey-Glass chaotic time series | - |
dc.subject.keywordAuthor | Minimum redundancy and maximum relevance (mRMR) | - |
dc.subject.keywordPlus | SYSTEMS | - |
dc.subject.keywordPlus | BACKPROPAGATION | - |
dc.subject.keywordPlus | CALCULUS | - |
dc.subject.keywordPlus | TIME | - |
dc.subject.keywordPlus | IDENTIFICATION | - |
dc.subject.keywordPlus | PREDICTION | - |
dc.subject.keywordPlus | MODELS | - |
dc.subject.keywordPlus | SERIES | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.