An EM-based algorithm for recurrent neural networks

A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM (expectation-maximization) algorithm with a mean field approximation is then applied to train recurrent networks through hidden state estimation. The resulting EM-b...

Full description

Saved in:
Bibliographic Details
Published inProceedings 1995 IEEE International Symposium on Information Theory p. 175
Main Authors Ma, S., Ji, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1995
Subjects
Computer networks
Convergence
Information theory
Jacobian matrices
Neural networks
Neurons
Recurrent neural networks
Testing
Online AccessGet full text
ISBN0780324536
9780780324534
DOI10.1109/ISIT.1995.531524

Cover

Abstract A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM (expectation-maximization) algorithm with a mean field approximation is then applied to train recurrent networks through hidden state estimation. The resulting EM-based algorithm, which reduces training the original recurrent network to training a set of individual feedforward neurons, simplifies the original training process and reduces the training time.
AbstractList A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM (expectation-maximization) algorithm with a mean field approximation is then applied to train recurrent networks through hidden state estimation. The resulting EM-based algorithm, which reduces training the original recurrent network to training a set of individual feedforward neurons, simplifies the original training process and reduces the training time.
Author Ji, C.
Ma, S.
Author_xml – sequence: 1
  givenname: S.
  surname: Ma
  fullname: Ma, S.
  organization: Dept. of Electr. Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
– sequence: 2
  givenname: C.
  surname: Ji
  fullname: Ji, C.
BookMark eNotj0FLwzAYQAMq6Obu4il_oDVfki9tj2NMV5h4cJ7H1-SrVrtWkg7x3zuY7_JuD95MXA7jwELcgcoBVPVQv9a7HKoKczSA2l6ImSpKZbRF467FIqVPdcJatApuhFkOcv2cNZQ4SOrfx9hNHwfZjlFG9scYeZjkwMdI_UnTzxi_0q24aqlPvPj3XLw9rnerTbZ9eapXy23WgbJT5pRGCI5Ild5j4cAjkbfGlkzBIAZumuCNJQeVYa8JQltoVBQCet2QmYv7c7dj5v137A4Uf_fnLfMH57tE4g
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISIT.1995.531524
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 Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 531524
GroupedDBID 6IE
6IK
6IL
AAJGR
AAWTH
ACGHX
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
OCL
RIE
RIL
ID FETCH-LOGICAL-i104t-60251d6aa08cc5761c5aac4348ead355debbdc34a6193ec2a1df7250add5c2ba3
IEDL.DBID RIE
ISBN 0780324536
9780780324534
IngestDate Tue Aug 26 16:58:45 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i104t-60251d6aa08cc5761c5aac4348ead355debbdc34a6193ec2a1df7250add5c2ba3
ParticipantIDs ieee_primary_531524
PublicationCentury 1900
PublicationDate 19950000
PublicationDateYYYYMMDD 1995-01-01
PublicationDate_xml – year: 1995
  text: 19950000
PublicationDecade 1990
PublicationTitle Proceedings 1995 IEEE International Symposium on Information Theory
PublicationTitleAbbrev ISIT
PublicationYear 1995
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000445401
Score 1.2356994
Snippet A stochastic model is established for fully-connected recurrent neural networks with sigmoid units based on Gibbs distributions. The EM...
SourceID ieee
SourceType Publisher
StartPage 175
SubjectTerms Computer networks
Convergence
Information theory
Jacobian matrices
Neural networks
Neurons
Recurrent neural networks
Testing
Title An EM-based algorithm for recurrent neural networks
URI https://ieeexplore.ieee.org/document/531524
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwELZoJyZeRbzlgdVpUj_ijAi1apGKkGilbpVjO1BRUtSmC7-eO6ctAjEwxclg2c7Jd9_5vs-E3AoUiPGiYHkCW6DgVjHjdcK0ApNW6EIFEoWHj6o_Fg8TOdnobAcujPc-FJ_5CJvhLN8t7BpTZW2wF9kRDdJItaqpWrt0SixQSi4JwFzHECVIrjb6Ott3sT2ljLP24HkwQqKejOo-f9ytElxL76DmbK-CIiFWlLxF6yqP7OcvvcZ_jvqQtL45fPRp552OyJ4vTwi_K2l3yNB1OWrmL4vlrHp9pxC40iUm3lGqiaLEpZnDIxSIr1pk3OuO7vtsc20CmwG2qphC2OCUMbG2FuBEYqUxVnChwWogvHA-z53lwgB24t52TOKKFCIh2Omk7eSGn5JmuSj9GaGZFI4bFLyxqch4nBXQmceF9mlSGH1OjnG-049aGWNaT_Xiz6-XZL-mg2P64oo0q-XaX4NDr_Kb8Cu_AGZLm0g
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT8IwFG4UD3ryF8bf7uC1Y6OvYzsaAwEFYiIk3EjXdkrEYWBc_Ot9rwOMxoOndTs0bffS977X931l7BZIIMZCxtMQt0AQOuLKxiGPIzTpiFwoEFG414_aQ3gYydFKZ9txYay1rvjM-tR0Z_lmppeUKquhvcg6bLMdCQCyJGttEioBkJhc6KB5HGCcIEW0UthZv8P6nDJIap3nzoCoetIve_1xu4pzLq39krW9cJqEVFPy5i-L1NefvxQb_znuA1b9ZvF5Txv_dMi2bH7MxF3uNXucnJfx1PRlNp8Ur-8ehq7enFLvJNbkkcilmuLDlYgvqmzYag7u23x1cQKfILoqeETAwURKBbHWCChCLZXSICBGu8EAw9g0NVqAQvQkrK6r0GQNjIVwr5O6nipxwir5LLenzEskGKFI8kY3IBFBkmFnlhbaNsJMxWfsiOY7_ii1McblVM___HrDdtuDXnfc7fQfL9heSQ6nZMYlqxTzpb1C916k1-63fgG-eZ6V
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+1995+IEEE+International+Symposium+on+Information+Theory&rft.atitle=An+EM-based+algorithm+for+recurrent+neural+networks&rft.au=Ma%2C+S.&rft.au=Ji%2C+C.&rft.date=1995-01-01&rft.pub=IEEE&rft.isbn=9780780324534&rft.spage=175&rft_id=info:doi/10.1109%2FISIT.1995.531524&rft.externalDocID=531524
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780324534/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780324534/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780780324534/sc.gif&client=summon&freeimage=true