A simplification of the backpropagation-through-time algorithm for optimal neurocontrol

Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPT...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on neural networks Ročník 8; číslo 2; s. 437 - 441
Hlavní autoři: Bersini, H., Gorrini, V.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.03.1997
Institute of Electrical and Electronics Engineers
Témata:
Applied sciences
Artificial intelligence
Backpropagation algorithms
Bioreactors
Calculus
Computer science; control theory; systems
Connectionism. Neural networks
Dynamic programming
Equations
Exact sciences and technology
Jacobian matrices
Lagrangian functions
Multi-layer neural network
Neural networks
Optimal control
State feedback
Backpropagation algorithm
Experimental result
Optimal control
Dynamic programming
Neural network
Optimization
Multilayer network
ISSN:1045-9227, 1941-0093
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor.
AbstractList Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor.Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor.
Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor
Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor.
Author Gorrini, V.
Bersini, H.
Author_xml – sequence: 1
  givenname: H.
  surname: Bersini
  fullname: Bersini, H.
  organization: IRIDIA-CP, Univ. Libre de Bruxelles, Belgium
– sequence: 2
  givenname: V.
  surname: Gorrini
  fullname: Gorrini, V.
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2631476$$DView record in Pascal Francis
https://www.ncbi.nlm.nih.gov/pubmed/18255645$$D View this record in MEDLINE/PubMed
BookMark eNp90c1vFSEQAHBiauyHHrx6MHswNR625WuW5dg01po08dLGI2FZeA9llxXYQ_97se_5Dsb0BBl-A8zMKTqa42wRekvwBSFYXgp6ASA62b9AJ0Ry0mIs2VHdYw6tpFQco9Ocf2BMOODuFTomPQXoOJyg71dN9tMSvPNGFx_nJrqmbG0zaPNzSXHRm6dwW7YprpttW_xkGx02MfmynRoXUxOXGtShme2aoolzSTG8Ri-dDtm-2a9n6OHm8_31bXv37cvX66u71rCOlNYSzQaAwQxMOFZLIHIUVLpRCj4IVoNCchjAkV5b6EawIGzfaykYd93I2Bn6uLu3_vXXanNRk8_GhqBnG9esqqNAeA9Vnj8raQ8S98ArfL-H6zDZUS2pVpce1d-mVfBhD3Q2OrikZ-PzwdGOES66yi53zKSYc7JOGV-emlmS9kERrP5MTwmqdtOrGZ_-yTi8_R_7bme9tfbg9oe_AYK2oV8
CODEN ITNNEP
CitedBy_id crossref_primary_10_1016_S0925_2312_98_00093_9
crossref_primary_10_1002__SICI_1099_1239_199909_9_11_799__AID_RNC441_3_0_CO_2_U
crossref_primary_10_1016_j_asoc_2006_02_010
crossref_primary_10_1109_72_977323
crossref_primary_10_1023_A_1007686309208
crossref_primary_10_1109_87_944469
crossref_primary_10_3390_a11080121
crossref_primary_10_1007_s11265_019_01485_2
Cites_doi 10.1016/0893-6080(94)90103-1
10.1109/IJCNN.1991.170615
10.1049/ip-f-2.1991.0009
10.1109/ICNN.1993.298851
10.1016/0893-6080(94)90067-1
10.1109/5.58337
10.1109/37.55119
ContentType Journal Article
Copyright 1997 INIST-CNRS
Copyright_xml – notice: 1997 INIST-CNRS
DBID AAYXX
CITATION
IQODW
NPM
7SC
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/72.557698
DatabaseName CrossRef
Pascal-Francis
PubMed
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Computer and Information Systems Abstracts

PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Anatomy & Physiology
Computer Science
Applied Sciences
EISSN 1941-0093
EndPage 441
ExternalDocumentID 18255645
2631476
10_1109_72_557698
557698
Genre orig-research
Journal Article
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
AAJGR
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
ACGFS
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
S10
TAE
TN5
VH1
AAYXX
CITATION
IQODW
RIG
NPM
7SC
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c361t-e1a3b55bcb37f376919d729fd974b7337f7945b5f18ae56d5e57e88a9734f6d33
IEDL.DBID RIE
ISICitedReferencesCount 21
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=10_1109_72_557698&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1045-9227
IngestDate Thu Sep 04 22:01:09 EDT 2025
Thu Sep 04 15:46:17 EDT 2025
Mon Jul 21 05:53:09 EDT 2025
Mon Jul 21 09:14:18 EDT 2025
Tue Nov 18 22:34:42 EST 2025
Sat Nov 29 03:59:16 EST 2025
Wed Aug 27 02:29:46 EDT 2025
IsPeerReviewed false
IsScholarly false
Issue 2
Keywords State feedback
Backpropagation algorithm
Experimental result
Optimal control
Dynamic programming
Neural network
Optimization
Multilayer network
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c361t-e1a3b55bcb37f376919d729fd974b7337f7945b5f18ae56d5e57e88a9734f6d33
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
PMID 18255645
PQID 28590854
PQPubID 23500
PageCount 5
ParticipantIDs ieee_primary_557698
pubmed_primary_18255645
crossref_citationtrail_10_1109_72_557698
crossref_primary_10_1109_72_557698
proquest_miscellaneous_734251485
proquest_miscellaneous_28590854
pascalfrancis_primary_2631476
PublicationCentury 1900
PublicationDate 1997-03-01
PublicationDateYYYYMMDD 1997-03-01
PublicationDate_xml – month: 03
  year: 1997
  text: 1997-03-01
  day: 01
PublicationDecade 1990
PublicationPlace New York, NY
PublicationPlace_xml – name: New York, NY
– name: United States
PublicationTitle IEEE transactions on neural networks
PublicationTitleAbbrev TNN
PublicationTitleAlternate IEEE Trans Neural Netw
PublicationYear 1997
Publisher IEEE
Institute of Electrical and Electronics Engineers
Publisher_xml – name: IEEE
– name: Institute of Electrical and Electronics Engineers
References ref7
feldkamp (ref3) 1993
saerens (ref8) 1991; 138
ref9
ungar (ref10) 1989
ref6
ref11
kirk (ref4) 1970
ref5
anderson iii (ref1) 1989
ref2
References_xml – ident: ref9
  doi: 10.1016/0893-6080(94)90103-1
– ident: ref6
  doi: 10.1109/IJCNN.1991.170615
– volume: 138
  start-page: 55
  year: 1991
  ident: ref8
  article-title: neural controller based on back-propagation algorithm
  publication-title: Radar and Signal Processing IEE Proceedings F
  doi: 10.1049/ip-f-2.1991.0009
– start-page: 451
  year: 1993
  ident: ref3
  article-title: neural network approaches to process control-the bioreactor benchmark problem
  publication-title: Proc World Congr Neural Networks
– ident: ref7
  doi: 10.1109/ICNN.1993.298851
– ident: ref2
  doi: 10.1016/0893-6080(94)90067-1
– ident: ref11
  doi: 10.1109/5.58337
– start-page: 475
  year: 1989
  ident: ref1
  article-title: challenging control problems
  publication-title: Neural Networks for Controls
– start-page: 154
  year: 1970
  ident: ref4
  publication-title: Optimal Control Theory&#x2014 An Introduction
– start-page: 387
  year: 1989
  ident: ref10
  article-title: a bioreactor benchmark for adaptive network-based process control
  publication-title: Neural Networks for Controls
– ident: ref5
  doi: 10.1109/37.55119
SSID ssj0014506
Score 1.2953365
Snippet Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal...
SourceID proquest
pubmed
pascalfrancis
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 437
SubjectTerms Applied sciences
Artificial intelligence
Backpropagation algorithms
Bioreactors
Calculus
Computer science; control theory; systems
Connectionism. Neural networks
Dynamic programming
Equations
Exact sciences and technology
Jacobian matrices
Lagrangian functions
Multi-layer neural network
Neural networks
Optimal control
Title A simplification of the backpropagation-through-time algorithm for optimal neurocontrol
URI https://ieeexplore.ieee.org/document/557698
https://www.ncbi.nlm.nih.gov/pubmed/18255645
https://www.proquest.com/docview/28590854
https://www.proquest.com/docview/734251485
Volume 8
WOSCitedRecordID wos10_1109_72_557698&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library
  customDbUrl:
  eissn: 1941-0093
  dateEnd: 20111231
  omitProxy: false
  ssIdentifier: ssj0014506
  issn: 1045-9227
  databaseCode: RIE
  dateStart: 19900101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61VQ9woLDlEaDFQghxSbt-xfZxhVpxQBUHEHuLYseGVbsJ2kel_nvGjncpUnvoLXIm0sQztr-xx98AfBgH7dqxY2XQVpTxZK-0hsrScW_Q_IxZly4Kf1UXF3o6Nd8yz3a6C-O9T8ln_iQ-prP8tnfruFV2KhEcG70Lu0pVw1Wt7YGBkKmMJgYXsjSMqUwiRMfmVLGT4cNIEKoj5Va8u3RrFUplVWJSZLPEfglDQYv7EWdaec4PHqTzU3iSASaZDB7xDHZ8N4LDSYfB9fyGfCQp5TPtpY_gYFPTgeQhPoLHtwgKD-HnhCxnMec85K090geCkJHYxl2i4jgbpeYyl_spY6l60lz96hez1e85QURMepyU5qhRYs7MmfHP4cf52ffPX8pcigGNVtFV6WnDrZTWWa4CzkmGmhZheWgxHLGKYyMaVloZqG68rFrppfJaN0ZxEaqW8xew1_WdfwXEsjZUNEjsmCCU0I0WFFEC954H7VVbwKeNaWqXecpjuYyrOsUrY1MrVg-9WsD7reifgZzjLqFRtMpWYNN69J-5t69ZxalQVQHvNuavccDFU5Sm8_16WUfGP8SpogByjwT-M6JGoWUBLwfH-add9r_Xdyr1Bh4N7Lgxxe0t7K0Wa38E--56NVsujtHtp_o4uf1fhpv_RQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BQaIcKGwpBCi1EEJc3CZ-xPZxhaiKWFYciugtihMbVnQTtA8k_j1jx7sUqT1wi5yJNPH48Y1n_A3A69zrps0bRr22gobIHrWmkLThzqD5GbNNvCg8UdOpvrgwnxPPdrwL45yLyWfuODzGWH7bN-twVHYiERwbfRvuSCFYPlzW2oYMhIyFNNG9kNQwphKNUJGbE8WOh08DRagOpFvh9tKVfSgWVglpkfUSe8YPJS1uxpxx7znd-y-tH8KDBDHJeBgTj-CW60awP-7QvZ7_Jm9ITPqMp-kj2NtUdSBpko_g_hWKwn34OibLWcg69-lwj_SeIGgktm5-oOK4HsVmmgr-0FCsntSX3_rFbPV9ThATkx6XpTlqFLkzU278Y_hy-v783RlNxRjQbGWxoq6ouZXSNpYrj6uSKUyLwNy36JBYxbERTSut9IWunSxb6aRyWtdGceHLlvMD2On6zj0FYlnry8JL7BgvlNC1FgXiBO4c99qpNoO3G9NUTWIqDwUzLqvoseSmUqwaejWDV1vRnwM9x3VCo2CVrcCm9fAfc29fs5IXQpUZHG3MX-GUC3GUunP9elkFzj9EqiIDcoME_jPiRqFlBk-GgfNXuzT-nl2r1BHcOzv_NKkmH6Yfn8PuwJUbEt5ewM5qsXaHcLf5tZotFy_j4P8D5joBsw
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%3Ajournal&rft.genre=article&rft.atitle=A+simplification+of+the+backpropagation-through-time+algorithm+for+optimal+neurocontrol&rft.jtitle=IEEE+transactions+on+neural+networks&rft.au=Bersini%2C+H&rft.au=Gorrini%2C+V&rft.date=1997-03-01&rft.issn=1045-9227&rft.volume=8&rft.issue=2&rft.spage=437&rft.epage=441&rft_id=info:doi/10.1109%2F72.557698&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1045-9227&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1045-9227&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1045-9227&client=summon