Fast training of multilayer perceptrons with a mixed norm algorithm

A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in...

Full description

Saved in:
Bibliographic Details
Main Authors: Abid, S., Fnaiech, F., Jervis, B.W., Cheriet, M.
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Back
Backpropagation algorithms
Biomedical imaging
Convergence
Laboratories
Least squares approximation
Least squares methods
Multilayer perceptrons
Neurons
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1022 vol. 2
container_issue
container_start_page 1018
container_title
container_volume 2
creator Abid, S.
Fnaiech, F.
Jervis, B.W.
Cheriet, M.
description A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in the hidden layers, an analogous back propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Experimental results on benchmark applications and a real medical problem are obtained which indicates significant reduction in the total number of iterations, the convergence time, and the generalization capacity when compared to those of the SBP algorithm.
doi_str_mv 10.1109/IJCNN.2005.1555992
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_1555992</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1555992</ieee_id><sourcerecordid>1555992</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-e82449b624a01318d6da5ced14353a13bd3f809fc8963614e52ee789e6c6a9323</originalsourceid><addsrcrecordid>eNo1j81KAzEURoM_YFt9Ad3kBWa8yU0yyVIGWyulbnRd0pk7NTJ_ZCLat1ewrj44Bw58jN0KyIUAd79-LrfbXALoXGitnZNnbCaFEZlSUJyzORQW0IGy8uJfoMMrNp-mDwCJzuGMlUs_JZ6iD33oD3xoePfZptD6I0U-UqxoTHHoJ_4V0jv3vAvfVPN-iB337WGIv7S7ZpeNbye6Oe2CvS0fX8unbPOyWpcPmyyIQqeMrFTK7Y1UHgQKW5va64pqoVCjF7ivsbHgmso6g0Yo0pKosI5MZbxDiQt299cNRLQbY-h8PO5O5_EHtNpMBg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Fast training of multilayer perceptrons with a mixed norm algorithm</title><source>IEEE Xplore All Conference Series</source><creator>Abid, S. ; Fnaiech, F. ; Jervis, B.W. ; Cheriet, M.</creator><creatorcontrib>Abid, S. ; Fnaiech, F. ; Jervis, B.W. ; Cheriet, M.</creatorcontrib><description>A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in the hidden layers, an analogous back propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Experimental results on benchmark applications and a real medical problem are obtained which indicates significant reduction in the total number of iterations, the convergence time, and the generalization capacity when compared to those of the SBP algorithm.</description><identifier>ISSN: 2161-4393</identifier><identifier>ISBN: 0780390482</identifier><identifier>ISBN: 9780780390485</identifier><identifier>EISSN: 2161-4407</identifier><identifier>DOI: 10.1109/IJCNN.2005.1555992</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial intelligence ; Back ; Backpropagation algorithms ; Biomedical imaging ; Convergence ; Laboratories ; Least squares approximation ; Least squares methods ; Multilayer perceptrons ; Neurons</subject><ispartof>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, 2005, Vol.2, p.1018-1022 vol. 2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1555992$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1555992$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Abid, S.</creatorcontrib><creatorcontrib>Fnaiech, F.</creatorcontrib><creatorcontrib>Jervis, B.W.</creatorcontrib><creatorcontrib>Cheriet, M.</creatorcontrib><title>Fast training of multilayer perceptrons with a mixed norm algorithm</title><title>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005</title><addtitle>IJCNN</addtitle><description>A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in the hidden layers, an analogous back propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Experimental results on benchmark applications and a real medical problem are obtained which indicates significant reduction in the total number of iterations, the convergence time, and the generalization capacity when compared to those of the SBP algorithm.</description><subject>Artificial intelligence</subject><subject>Back</subject><subject>Backpropagation algorithms</subject><subject>Biomedical imaging</subject><subject>Convergence</subject><subject>Laboratories</subject><subject>Least squares approximation</subject><subject>Least squares methods</subject><subject>Multilayer perceptrons</subject><subject>Neurons</subject><issn>2161-4393</issn><issn>2161-4407</issn><isbn>0780390482</isbn><isbn>9780780390485</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j81KAzEURoM_YFt9Ad3kBWa8yU0yyVIGWyulbnRd0pk7NTJ_ZCLat1ewrj44Bw58jN0KyIUAd79-LrfbXALoXGitnZNnbCaFEZlSUJyzORQW0IGy8uJfoMMrNp-mDwCJzuGMlUs_JZ6iD33oD3xoePfZptD6I0U-UqxoTHHoJ_4V0jv3vAvfVPN-iB337WGIv7S7ZpeNbye6Oe2CvS0fX8unbPOyWpcPmyyIQqeMrFTK7Y1UHgQKW5va64pqoVCjF7ivsbHgmso6g0Yo0pKosI5MZbxDiQt299cNRLQbY-h8PO5O5_EHtNpMBg</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Abid, S.</creator><creator>Fnaiech, F.</creator><creator>Jervis, B.W.</creator><creator>Cheriet, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2005</creationdate><title>Fast training of multilayer perceptrons with a mixed norm algorithm</title><author>Abid, S. ; Fnaiech, F. ; Jervis, B.W. ; Cheriet, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-e82449b624a01318d6da5ced14353a13bd3f809fc8963614e52ee789e6c6a9323</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Artificial intelligence</topic><topic>Back</topic><topic>Backpropagation algorithms</topic><topic>Biomedical imaging</topic><topic>Convergence</topic><topic>Laboratories</topic><topic>Least squares approximation</topic><topic>Least squares methods</topic><topic>Multilayer perceptrons</topic><topic>Neurons</topic><toplevel>online_resources</toplevel><creatorcontrib>Abid, S.</creatorcontrib><creatorcontrib>Fnaiech, F.</creatorcontrib><creatorcontrib>Jervis, B.W.</creatorcontrib><creatorcontrib>Cheriet, M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEL</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Abid, S.</au><au>Fnaiech, F.</au><au>Jervis, B.W.</au><au>Cheriet, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Fast training of multilayer perceptrons with a mixed norm algorithm</atitle><btitle>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005</btitle><stitle>IJCNN</stitle><date>2005</date><risdate>2005</risdate><volume>2</volume><spage>1018</spage><epage>1022 vol. 2</epage><pages>1018-1022 vol. 2</pages><issn>2161-4393</issn><eissn>2161-4407</eissn><isbn>0780390482</isbn><isbn>9780780390485</isbn><abstract>A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in the hidden layers, an analogous back propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Experimental results on benchmark applications and a real medical problem are obtained which indicates significant reduction in the total number of iterations, the convergence time, and the generalization capacity when compared to those of the SBP algorithm.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN.2005.1555992</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2161-4393
ispartof Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, 2005, Vol.2, p.1018-1022 vol. 2
issn 2161-4393
2161-4407
language eng
recordid cdi_ieee_primary_1555992
source IEEE Xplore All Conference Series
subjects Artificial intelligence
Back
Backpropagation algorithms
Biomedical imaging
Convergence
Laboratories
Least squares approximation
Least squares methods
Multilayer perceptrons
Neurons
title Fast training of multilayer perceptrons with a mixed norm algorithm
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T02%3A03%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Fast%20training%20of%20multilayer%20perceptrons%20with%20a%20mixed%20norm%20algorithm&rft.btitle=Proceedings.%202005%20IEEE%20International%20Joint%20Conference%20on%20Neural%20Networks,%202005&rft.au=Abid,%20S.&rft.date=2005&rft.volume=2&rft.spage=1018&rft.epage=1022%20vol.%202&rft.pages=1018-1022%20vol.%202&rft.issn=2161-4393&rft.eissn=2161-4407&rft.isbn=0780390482&rft.isbn_list=9780780390485&rft_id=info:doi/10.1109/IJCNN.2005.1555992&rft_dat=%3Cieee_CHZPO%3E1555992%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-e82449b624a01318d6da5ced14353a13bd3f809fc8963614e52ee789e6c6a9323%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1555992&rfr_iscdi=true