Identification of Finite State Automata With a Class of Recurrent Neural Networks

Cited 13 time in webofscience Cited 0 time in scopus
  • Hit : 479
  • Download : 152
DC FieldValueLanguage
dc.contributor.authorWon, Sung-Hwanko
dc.contributor.authorSong, Iickhoko
dc.contributor.authorLee, Sun Youngko
dc.contributor.authorPark, Cheol-Hoonko
dc.date.accessioned2013-03-11T19:56:41Z-
dc.date.available2013-03-11T19:56:41Z-
dc.date.created2012-02-06-
dc.date.created2012-02-06-
dc.date.issued2010-09-
dc.identifier.citationIEEE TRANSACTIONS ON NEURAL NETWORKS, v.21, pp.1408 - 1421-
dc.identifier.issn1045-9227-
dc.identifier.urihttp://hdl.handle.net/10203/100110-
dc.description.abstractA class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in the encoding, identification, and extraction of finite state automata (FSAs). Simulation results show that the identification of FSAs using the proposed network, trained by the hybrid greedy simulated annealing with a modified cost function in the training stage, generally exhibits better performance than the conventional identification procedures.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectLEVENBERG-MARQUARDT ALGORITHM-
dc.subjectSYSTEMS-
dc.subjectTIME-
dc.subjectINFERENCE-
dc.subjectMACHINES-
dc.subjectNETS-
dc.titleIdentification of Finite State Automata With a Class of Recurrent Neural Networks-
dc.typeArticle-
dc.identifier.wosid000283231200003-
dc.identifier.scopusid2-s2.0-77956343714-
dc.type.rimsART-
dc.citation.volume21-
dc.citation.beginningpage1408-
dc.citation.endingpage1421-
dc.citation.publicationnameIEEE TRANSACTIONS ON NEURAL NETWORKS-
dc.identifier.doi10.1109/TNN.2010.2059040-
dc.embargo.liftdate9999-12-31-
dc.embargo.terms9999-12-31-
dc.contributor.localauthorSong, Iickho-
dc.contributor.localauthorPark, Cheol-Hoon-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorCost function-
dc.subject.keywordAuthorfinite state automaton (FSA)-
dc.subject.keywordAuthorhybrid greedy simulated annealing (HGSA)-
dc.subject.keywordAuthorrecurrent neural network (RNN)-
dc.subject.keywordAuthorsystem identification-
dc.subject.keywordPlusLEVENBERG-MARQUARDT ALGORITHM-
dc.subject.keywordPlusSYSTEMS-
dc.subject.keywordPlusTIME-
dc.subject.keywordPlusINFERENCE-
dc.subject.keywordPlusMACHINES-
dc.subject.keywordPlusNETS-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 13 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0