Boundedness of estimator with an improved back propagation algorithm

This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The learning gain is decided by the 'Levenberg-Marquardt' algorithm, which is a nonlinear least squares method. The boundedness of the weighti...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the 1996 IEEE IECON : 22nd International Conference on Industrial Electronics, Control, and Instrumentation Ročník 1; s. 309 - 314 vol.1
Hlavní autoři: Ikeda, K., Shin, S.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 1996
Témata:
ISBN:0780327756, 9780780327757
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The learning gain is decided by the 'Levenberg-Marquardt' algorithm, which is a nonlinear least squares method. The boundedness of the weightings is shown from a viewpoint of the robust adaptive control theory and a relationship between data sizes and learning rates is considered. Furthermore, simple numerical simulations are presented to show the efficiency of the proposed learning algorithm.
AbstractList This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The learning gain is decided by the 'Levenberg-Marquardt' algorithm, which is a nonlinear least squares method. The boundedness of the weightings is shown from a viewpoint of the robust adaptive control theory and a relationship between data sizes and learning rates is considered. Furthermore, simple numerical simulations are presented to show the efficiency of the proposed learning algorithm.
Author Shin, S.
Ikeda, K.
Author_xml – sequence: 1
  givenname: K.
  surname: Ikeda
  fullname: Ikeda, K.
  organization: Dept. of Math. Eng. & Inf. Phys., Tokyo Univ., Japan
– sequence: 2
  givenname: S.
  surname: Shin
  fullname: Shin, S.
BookMark eNotj81OwzAQhC0BErT0AeDkF0hwsv6JjxBaqFTRC5yrrbMuhiaO4gDi7YlU5jJzGI2-mbHzLnbE2E0h8qIQ9m69rLcveWGtzpUR1ogzNhOmElAao_QlW6T0ISZJpUBUV-zxIX51DTUdpcSj55TG0OIYB_4TxneOHQ9tP8Rvavge3Sefco8HHEPsOB4PcZha7TW78HhMtPj3OXtbLV_r52yzfVrX95ssFEKOGZJED84bdOSsJkGyqVApAqxUCaVXIMGSrCY0ZYzWzoMksLD3xmlpYc5uT7uBiHb9MJEOv7vTT_gDWQVLaA
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IECON.1996.570970
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library Online
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Education
Physics
EndPage 314 vol.1
ExternalDocumentID 570970
GroupedDBID 6IE
6IK
6IL
AAJGR
AAWTH
ACGHX
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
OCL
RIE
RIL
ID FETCH-LOGICAL-i104t-ae4af3cf7acec96e0e4d8a55e3a85232f53439e4853057766cf34e393bf7c6493
IEDL.DBID RIE
ISBN 0780327756
9780780327757
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=570970&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Tue Aug 26 17:37:16 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i104t-ae4af3cf7acec96e0e4d8a55e3a85232f53439e4853057766cf34e393bf7c6493
ParticipantIDs ieee_primary_570970
PublicationCentury 1900
PublicationDate 19960000
PublicationDateYYYYMMDD 1996-01-01
PublicationDate_xml – year: 1996
  text: 19960000
PublicationDecade 1990
PublicationTitle Proceedings of the 1996 IEEE IECON : 22nd International Conference on Industrial Electronics, Control, and Instrumentation
PublicationTitleAbbrev IECON
PublicationYear 1996
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000455308
Score 1.3663247
Snippet This paper proposes a novel learning algorithm with a variable learning gain and a /spl sigma/-modification term for a multilayered neural network. The...
SourceID ieee
SourceType Publisher
StartPage 309
SubjectTerms Adaptive control
Education
Filters
Gain
Multi-layer neural network
Neural networks
Neurons
Physics
Robust control
Upper bound
Title Boundedness of estimator with an improved back propagation algorithm
URI https://ieeexplore.ieee.org/document/570970
Volume 1
WOSCitedRecordID wos570970&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwELWgAgkuQChilw9cU5yM4-XKUsGl6gGk3irXGaMKmqAufD-2EwpIXLg5UWRFjuKZ9zzzHiFXufQ_jQisjRE25TnqVFvAFJgrPaDIGGYmmk3IwUCNRnrY6mzHXhhEjMVn2AvDeJZf1nYVqDIP3pmWHp9vSimaVq01neIzkwKYisBcMcilLESrr_N1LdtDzYzp68dgExg69USvmfSXuUqMLf29f73VPul-9-jR4Tr6HJANrJLgwdzWayRk94fUYEK2Y6mnXRySu5vgpIRl2ONo7WiQ2ZgF6E0DJ0tNRaeRaMCSTox9pX7sN504KTVvL_XcPzXrkuf-_dPtQ9p6KaRTD7iWqUFuHFgnjUWrBTLkpTJFgWCUx6K5K8CnJsh99PYZnBTCOuAIGiZOWsE1HJFOVVd4TChAIblPHEyw7dEMVelKmFihMuBGKndCkrBI4_dGLmPcrM_pn3fPyE5TBh04jXPSWc5XeEG27Mdyuphfxk_8Ccksow0
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwELUQi4ALEIrY8YFrihM7Xq4sVStK1UOReqtcZ4wqaIK68P3YTiggceHmRJEVOYpn3vPMewhdp8L9NNyzNpqbmKWgYmUoxJTY3AGKhECig9mE6PXkcKj6tc526IUBgFB8Bk0_DGf5eWmWnipz4J0o4fD5hjfOqpu1VoSKy00ySmSA5pLQVIiM1wo7X9eiPtZMiLrpeKNA36vHm9W0v-xVQnRp7f3rvfZR47tLD_dX8ecArUEReRfmumIjQrs_xAYjtBWKPc38EN3fei8lyP0uh0uLvdDG1INv7FlZrAs8CVQD5HiszSt2Y7fthEmxfnspZ-6paQM9tx4Gd-24dlOIJw5yLWINTFtqrNAGjOJAgOVSZxlQLR0aTW1GXXICzMVvl8MJzo2lDKiiYysMZ4oeofWiLOAYYUozwVzqoL1xjyIgc5vTseEyoUwLaU9Q5Bdp9F4JZoyq9Tn98-4V2m4Pnrqjbqf3eIZ2qqJoz3Cco_XFbAkXaNN8LCbz2WX43J960aZW
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+1996+IEEE+IECON+%3A+22nd+International+Conference+on+Industrial+Electronics%2C+Control%2C+and+Instrumentation&rft.atitle=Boundedness+of+estimator+with+an+improved+back+propagation+algorithm&rft.au=Ikeda%2C+K.&rft.au=Shin%2C+S.&rft.date=1996-01-01&rft.pub=IEEE&rft.isbn=9780780327757&rft.volume=1&rft.spage=309&rft.epage=314+vol.1&rft_id=info:doi/10.1109%2FIECON.1996.570970&rft.externalDocID=570970
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780327757/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780327757/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780327757/sc.gif&client=summon&freeimage=true