A novel neural network training technique based on a multi-algorithm constrained optimization strategy

A novel methodology for efficient offline training of multilayer perceptrons (MLPs) is presented. The training is formulated as an optimization problem subject to box-constraints for the weights, so as to enhance the network's generalization capability. An optimization strategy is used combinin...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings. 24th EUROMICRO Conference (Cat. No.98EX204) Vol. 2; pp. 683 - 687 vol.2
Main Authors: Karras, D.A., Lagaris, I.E.
Format: Conference Proceeding
Language:English
Published: IEEE 1998
Subjects:
Backpropagation algorithms
Constraint optimization
Informatics
Multilayer perceptrons
Neural networks
Optimization methods
Organizing
Robustness
Search methods
Weight control
ISBN:9780818686467, 0818686464
ISSN:1089-6503
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract A novel methodology for efficient offline training of multilayer perceptrons (MLPs) is presented. The training is formulated as an optimization problem subject to box-constraints for the weights, so as to enhance the network's generalization capability. An optimization strategy is used combining variable metric, conjugate gradient and no-derivative pattern search methods that renders the training process robust and efficient. The superiority of this approach, over Off-line Backpropagation algorithm, the RPROP training procedure as well as over the stand alone algorithms involved in the proposed complex optimization strategy, is demonstrated by direct application to two real world benchmarks and the parity-4 problem. These problems have been obtained from a standard collection of such benchmarks and special care has been taken on the statistical significance of the results by organizing the experimental study so as to compare the averages and variances of the training and generalization performance of the algorithms involved.
AbstractList A novel methodology for efficient offline training of multilayer perceptrons (MLPs) is presented. The training is formulated as an optimization problem subject to box-constraints for the weights, so as to enhance the network's generalization capability. An optimization strategy is used combining variable metric, conjugate gradient and no-derivative pattern search methods that renders the training process robust and efficient. The superiority of this approach, over Off-line Backpropagation algorithm, the RPROP training procedure as well as over the stand alone algorithms involved in the proposed complex optimization strategy, is demonstrated by direct application to two real world benchmarks and the parity-4 problem. These problems have been obtained from a standard collection of such benchmarks and special care has been taken on the statistical significance of the results by organizing the experimental study so as to compare the averages and variances of the training and generalization performance of the algorithms involved.
Author Karras, D.A.
Lagaris, I.E.
Author_xml – sequence: 1
  givenname: D.A.
  surname: Karras
  fullname: Karras, D.A.
  organization: Dept. of Inf., Ioannina Univ., Greece
– sequence: 2
  givenname: I.E.
  surname: Lagaris
  fullname: Lagaris, I.E.
BookMark eNotkFFPwjAUhZuIiYj8AZ76B4a3a7e2j4SgkmBMjDyTu-0WqluHW9HgrxfEp3Ny8p3zcG7ZILSBGJsImAoB9n6xfn1ezqfCWjPVYMCYKza2-mSEyU2ucj1gQwHGJnkG8oaN-_4dAATITCo1ZG7GQ_tFNQ906PAs8bvtPnjs0AcftjxSuQv-80C8wJ4q3gaOvDnU0SdYb9vOx13Dyzb0f40zsI--8T8Y_Qk9p5G2xzt27bDuafyvI7Z-WLzNn5LVy-NyPlslXmgVk5IqU2UIWMoSlJUpWVSFQkMSs0po6QoAZ1VJeeXICZerClJtIRUpGl3IEZtcdj0Rbfadb7A7bi7HyF_qmFwj
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/EURMIC.1998.708088
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EndPage 687 vol.2
ExternalDocumentID 708088
GroupedDBID 23M
29G
6IE
6IF
6IH
6IK
6IL
AAJGR
AAWTH
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i174t-ced8d5a0ac3c04932e9a4b4a8e3a5d173fb00f94ce6dfef1f64d02790212a87b3
IEDL.DBID RIE
ISBN 9780818686467
0818686464
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000075882900106&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1089-6503
IngestDate Tue Aug 26 17:35:55 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i174t-ced8d5a0ac3c04932e9a4b4a8e3a5d173fb00f94ce6dfef1f64d02790212a87b3
ParticipantIDs ieee_primary_708088
PublicationCentury 1900
PublicationDate 19980000
PublicationDateYYYYMMDD 1998-01-01
PublicationDate_xml – year: 1998
  text: 19980000
PublicationDecade 1990
PublicationTitle Proceedings. 24th EUROMICRO Conference (Cat. No.98EX204)
PublicationTitleAbbrev EURMIC
PublicationYear 1998
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001035344
ssj0020048
Score 1.4047569
Snippet A novel methodology for efficient offline training of multilayer perceptrons (MLPs) is presented. The training is formulated as an optimization problem subject...
SourceID ieee
SourceType Publisher
StartPage 683
SubjectTerms Backpropagation algorithms
Constraint optimization
Informatics
Multilayer perceptrons
Neural networks
Optimization methods
Organizing
Robustness
Search methods
Weight control
Title A novel neural network training technique based on a multi-algorithm constrained optimization strategy
URI https://ieeexplore.ieee.org/document/708088
Volume 2
WOSCitedRecordID wos000075882900106&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/eLvHCXMwlV3NT8IwFG-EeNALihi_04PXwUa7tjsaA_FgCDFiuJF-vCkJbAYGif-9bbeBJl687CtbunV9e31v7_f7IXRPYu6sRgUQgQhorFQgZWzsQgmtDDDmufTenvloJKbTZFzxbHssDAD44jPouk3_L9_keuNSZT1upzdCNFCDc1ZCtfbplJDEXjGiirXcyCxr6111R0g89aOjhmeU0Yp4p97nNZgmTHqDyYt9fIfhE92yuV-yK97rDFv_ut8T1Nmj9_B455dO0QFkbdSq5RtwZc1tdPyDi_AMpQ84y7ewwI7hUrqVrw_HtYYE3rG9Yuf5DM4zLLGvRwzk4j1fzYuPJdZuuumucCfYr9GygnnidcmC-9VBk-Hg9fEpqEQYgrkNVopAgxEmlqHURNtogvQhkVRRKYDYdxpxklrDTROqgZkU0ihl1NhQN3HU8VJwRc5RM8szuEBYssRoSghJiKJcpaoPihPgYOLQqIhdorbrw9lnybMxK7vv6s-j1-ioRAe6ZMgNaharDdyiQ70t5uvVnR8b35QHt7s
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEN4omqgXFDG-3YPXQmG33e3RGAhGJMSA4Ub2MVUSaA2vxH_v7rYFTbx46Stt2kx3OjvT-b4PoXsSMOs10oMGcI8GUnpCBNosJFdSQxg6Lr23Luv1-GgU9XOebYeFAQDXfAY1u-n-5etUrWyprM7M9IbzXbQXUNr0M7DWtqDik8BpRuTZlh2bWXe97e_wiSN_tOTwIQ1pTr1T7LMCTuNH9dbw1RjAovh4LbvhL-EVF3fa5X898TGqbvF7uL-JTCdoB5IKKhcCDjj35wo6-sFGeIriB5yka5hiy3Ep7Mp1iONCRQJv-F6xjX0apwkW2HUkemL6ns4ny48ZVnbCaa-wJ5jv0SwHeuJFxoP7VUXDdmvw2PFyGQZvYtKVpadAcx0IXyiiTD5BmhAJKqngQMxbbTASG9eNI6og1DHEjTik2iS7kSWPF5xJcoZKSZrAOcIijLSihJCISMpkLJsgGQEGOvC1bIQXqGJtOP7MmDbGmfku_zx6hw46g5fuuPvUe75ChxlW0JZGrlFpOV_BDdpX6-VkMb914-QbUUG7Ag
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.+24th+EUROMICRO+Conference+%28Cat.+No.98EX204%29&rft.atitle=A+novel+neural+network+training+technique+based+on+a+multi-algorithm+constrained+optimization+strategy&rft.au=Karras%2C+D.A.&rft.au=Lagaris%2C+I.E.&rft.date=1998-01-01&rft.pub=IEEE&rft.isbn=9780818686467&rft.issn=1089-6503&rft.volume=2&rft.spage=683&rft.epage=687+vol.2&rft_id=info:doi/10.1109%2FEURMIC.1998.708088&rft.externalDocID=708088
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-6503&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-6503&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-6503&client=summon