Cellular SRN Trained by Extended Kalman Filter Shows Promise for ADP

Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP's, in particular for solving approximate dynamic programming problems. The 2D maze navigation has been considered as a proof-of-concept task. Present work improves the prev...

Full description

Saved in:
Bibliographic Details
Published in:The 2006 IEEE International Joint Conference on Neural Network Proceedings pp. 506 - 510
Main Authors: Ilin, R., Kozma, R., Werbos, P.J.
Format: Conference Proceeding
Language:English
Published: IEEE 2006
Subjects:
Cellular networks
Convergence
Cost function
Dynamic programming
Electronic mail
Equations
Learning
Navigation
Neural networks
Recurrent neural networks
ISBN:9780780394902, 0780394909
ISSN:2161-4393
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP's, in particular for solving approximate dynamic programming problems. The 2D maze navigation has been considered as a proof-of-concept task. Present work improves the previous results by training the network with extended Kalman filter (EKF). The original EKF algorithm has been slightly modified. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results. The implications of this improvement are discussed.
AbstractList Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP's, in particular for solving approximate dynamic programming problems. The 2D maze navigation has been considered as a proof-of-concept task. Present work improves the previous results by training the network with extended Kalman filter (EKF). The original EKF algorithm has been slightly modified. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results. The implications of this improvement are discussed.
Author Werbos, P.J.
Kozma, R.
Ilin, R.
Author_xml – sequence: 1
  givenname: R.
  surname: Ilin
  fullname: Ilin, R.
  organization: Memphis Univ., Memphis
– sequence: 2
  givenname: R.
  surname: Kozma
  fullname: Kozma, R.
  organization: Memphis Univ., Memphis
– sequence: 3
  givenname: P.J.
  surname: Werbos
  fullname: Werbos, P.J.
BookMark eNotj9tKw0AURQesYFv7AeLL_EDimUsyM48lvVgtsWjey2RyBiO5yCSi_XsDChv2etgs2Asy6_oOCbljEDMG5uHwlOV5zAHSmMtUcXlFVkZpmCKMNMBnZM5ZyiIpjLghi2H4AODCGDEnmwyb5quxgb695rQItu6wouWFbn9G7KqJn23T2o7u6mbEafXefw_0FPq2HpD6PtD15nRLrr1tBlz995IUu22RPUbHl_0hWx-j2sAY2QoS6SwDK5xmJaJEZTw6451TElCkZaolskSD84obX7m00toqzZi1Sooluf_T1oh4_gx1a8PlzNR0TSTiF0ELS-A
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/IJCNN.2006.246724
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EndPage 510
ExternalDocumentID 1716135
Genre orig-research
GroupedDBID 29I
29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i90t-ad054ca10a3c81bee4e79fec9fcc740e36b684e1580cf729fdc6d88a7811aa743
IEDL.DBID RIE
ISBN 9780780394902
0780394909
ISSN 2161-4393
IngestDate Wed Aug 27 01:50:29 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-ad054ca10a3c81bee4e79fec9fcc740e36b684e1580cf729fdc6d88a7811aa743
PageCount 5
ParticipantIDs ieee_primary_1716135
PublicationCentury 2000
PublicationDate 20060000
PublicationDateYYYYMMDD 2006-01-01
PublicationDate_xml – year: 2006
  text: 20060000
PublicationDecade 2000
PublicationTitle The 2006 IEEE International Joint Conference on Neural Network Proceedings
PublicationTitleAbbrev IJCNN
PublicationYear 2006
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0023993
ssj0000454271
Score 1.4214513
Snippet Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP's, in particular for solving...
SourceID ieee
SourceType Publisher
StartPage 506
SubjectTerms Cellular networks
Convergence
Cost function
Dynamic programming
Electronic mail
Equations
Learning
Navigation
Neural networks
Recurrent neural networks
Title Cellular SRN Trained by Extended Kalman Filter Shows Promise for ADP
URI https://ieeexplore.ieee.org/document/1716135
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFH5qKwamAi3ilgdGQl3n9Ih6iEtRBR26VbbzLCqFFPUA8e-x3TRlYGFLItmK7MTve8f3PYBrzbRlhgjP9xU1DkqoPCl16GkrHiUpQ66cZP5znKbJZMJHNbipuDCI6IrP8NZeulx-NldrGyrrWGmXrh_WoR7H0YarVcVTrJQci6vyDkvZtNllZkZ4xuj6zmVPqM8DTnmpvLO9Z2W6s0t55-Gxl6abJAUzh4hlwv9qu-KszrD5v_c9gPaOvkdGlWE6hBoWR9Dc9m8g5e_cgn4P89yWoZLXl5SMbbMIzIj8JoMyMk6eRP4uCjKc5W7g2_xraWc23wYSg3bJXX_UhvFwMO7de2VXBW_G6coTmQFpSpjt8ZWBrIgBxlyj4lqpOKDoRzJKAuyGCVXaIG-dqShLEmEZqUIYvHEMjWJe4AmQMEIeSJlJbZyqWDPOBNWByJyPqMLkFFp2TaYfG92MabkcZ38_Pof9XXjjAhqrxRovYU99rmbLxZXb7B_E4qIx
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLZKQYKpQIu48cBIqOucHlEPtbREFWToVtnOs6gUUtQDxL_HdkPKwMKWRLIV2Ynf947vewjdKqoMM4Q7riuJdlB86QihfEcZ8ShBKDBpJfNHYRxHkwkbV9BdyYUBAFt8Bvfm0uby07lcm1BZ00i7tFx_B-36nkfJhq1VRlSMmBwNywIPQ9o0-WWqxzja7LrWaY-IyzxGWKG983NPi4Rni7Dm4LEdx5s0BdXHiOHC_2q8Yu1Or_a_Nz5EjS2BD49L03SEKpAfo9pPBwdc_NB11GlDlplCVPzyHOPEtIuAFIsv3C1i43jIszee494sswNf559LM7P-OgBrvIsfOuMGSnrdpN13ir4KzoyRlcNTDdMk1xvkSg1aATwImQLJlJShR8ANRBB50PIjIpXG3iqVQRpF3HBSOdeI4wRV83kOpwj7ATBPiFQo7VaFijLKifJ4ar1E6UdnqG7WZPq-Uc6YFstx_vfjG7TfT55G09EgHl6gg22w4xJVV4s1XKE9-bGaLRfXduO_AWz2pXg
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=The+2006+IEEE+International+Joint+Conference+on+Neural+Network+Proceedings&rft.atitle=Cellular+SRN+Trained+by+Extended+Kalman+Filter+Shows+Promise+for+ADP&rft.au=Ilin%2C+R.&rft.au=Kozma%2C+R.&rft.au=Werbos%2C+P.J.&rft.date=2006-01-01&rft.pub=IEEE&rft.isbn=9780780394902&rft.issn=2161-4393&rft.spage=506&rft.epage=510&rft_id=info:doi/10.1109%2FIJCNN.2006.246724&rft.externalDocID=1716135
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2161-4393&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2161-4393&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2161-4393&client=summon