A parallel design and implementation for backpropagation neural network using MIMD architecture

The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fathy, S.K., Syiam, M.M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1475 vol.3
container_issue
container_start_page 1472
container_title
container_volume 3
creator Fathy, S.K.
Syiam, M.M.
description The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The developed parallel backpropagation algorithm is applied to the problem of printed Arabic character recognition. The experimental results revealed that the speed up approaches the maximum value of 15.2 when a network of 16-transputers is utilized.
doi_str_mv 10.1109/MELCON.1996.551228
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_551228</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>551228</ieee_id><sourcerecordid>551228</sourcerecordid><originalsourceid>FETCH-ieee_primary_5512283</originalsourceid><addsrcrecordid>eNp9jsFqwzAQRAWlkKb1D-S0PxBXsqI2PgbHJYU4veRuNvbGVSPLQpIp_fsY0nPm8mAeA8PYQvBUCJ6_VuW--DqkIs_fUqVElq0f2Jy_r7mUk1YzloTww6eslMqkfGL1Bhx6NIYMtBR0ZwFtC7p3hnqyEaMeLJwHDydsLs4PDrtbZ2mcdhPi7-AvMAZtO6g-qy2gb751pCaOnl7Y4xlNoOSfz2zxUR6L3VITUe287tH_1ber8q68AhuNRLk</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A parallel design and implementation for backpropagation neural network using MIMD architecture</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Fathy, S.K. ; Syiam, M.M.</creator><creatorcontrib>Fathy, S.K. ; Syiam, M.M.</creatorcontrib><description>The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The developed parallel backpropagation algorithm is applied to the problem of printed Arabic character recognition. The experimental results revealed that the speed up approaches the maximum value of 15.2 when a network of 16-transputers is utilized.</description><identifier>ISBN: 0780331095</identifier><identifier>ISBN: 9780780331099</identifier><identifier>DOI: 10.1109/MELCON.1996.551228</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Backpropagation algorithms ; Character recognition ; Computer architecture ; Computer networks ; Convergence ; Neural networks ; Neurons ; Parallel algorithms ; Training data</subject><ispartof>Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96), 1996, Vol.3, p.1472-1475 vol.3</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/551228$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,782,786,791,792,2062,4054,4055,27934,54929</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/551228$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Fathy, S.K.</creatorcontrib><creatorcontrib>Syiam, M.M.</creatorcontrib><title>A parallel design and implementation for backpropagation neural network using MIMD architecture</title><title>Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96)</title><addtitle>MELCON</addtitle><description>The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The developed parallel backpropagation algorithm is applied to the problem of printed Arabic character recognition. The experimental results revealed that the speed up approaches the maximum value of 15.2 when a network of 16-transputers is utilized.</description><subject>Algorithm design and analysis</subject><subject>Backpropagation algorithms</subject><subject>Character recognition</subject><subject>Computer architecture</subject><subject>Computer networks</subject><subject>Convergence</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Parallel algorithms</subject><subject>Training data</subject><isbn>0780331095</isbn><isbn>9780780331099</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1996</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9jsFqwzAQRAWlkKb1D-S0PxBXsqI2PgbHJYU4veRuNvbGVSPLQpIp_fsY0nPm8mAeA8PYQvBUCJ6_VuW--DqkIs_fUqVElq0f2Jy_r7mUk1YzloTww6eslMqkfGL1Bhx6NIYMtBR0ZwFtC7p3hnqyEaMeLJwHDydsLs4PDrtbZ2mcdhPi7-AvMAZtO6g-qy2gb751pCaOnl7Y4xlNoOSfz2zxUR6L3VITUe287tH_1ber8q68AhuNRLk</recordid><startdate>1996</startdate><enddate>1996</enddate><creator>Fathy, S.K.</creator><creator>Syiam, M.M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1996</creationdate><title>A parallel design and implementation for backpropagation neural network using MIMD architecture</title><author>Fathy, S.K. ; Syiam, M.M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_5512283</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1996</creationdate><topic>Algorithm design and analysis</topic><topic>Backpropagation algorithms</topic><topic>Character recognition</topic><topic>Computer architecture</topic><topic>Computer networks</topic><topic>Convergence</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Parallel algorithms</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>Fathy, S.K.</creatorcontrib><creatorcontrib>Syiam, M.M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fathy, S.K.</au><au>Syiam, M.M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A parallel design and implementation for backpropagation neural network using MIMD architecture</atitle><btitle>Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96)</btitle><stitle>MELCON</stitle><date>1996</date><risdate>1996</risdate><volume>3</volume><spage>1472</spage><epage>1475 vol.3</epage><pages>1472-1475 vol.3</pages><isbn>0780331095</isbn><isbn>9780780331099</isbn><abstract>The paper illustrates a parallel backpropagation algorithm that depends upon a transputer network. Since the backpropagation algorithm is regarded as being communication intensive, a mechanism is developed to decrease the communication time overhead between different related processor elements. The developed parallel backpropagation algorithm is applied to the problem of printed Arabic character recognition. The experimental results revealed that the speed up approaches the maximum value of 15.2 when a network of 16-transputers is utilized.</abstract><pub>IEEE</pub><doi>10.1109/MELCON.1996.551228</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 0780331095
ispartof Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96), 1996, Vol.3, p.1472-1475 vol.3
issn
language eng
recordid cdi_ieee_primary_551228
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Algorithm design and analysis
Backpropagation algorithms
Character recognition
Computer architecture
Computer networks
Convergence
Neural networks
Neurons
Parallel algorithms
Training data
title A parallel design and implementation for backpropagation neural network using MIMD architecture
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-02T17%3A44%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20parallel%20design%20and%20implementation%20for%20backpropagation%20neural%20network%20using%20MIMD%20architecture&rft.btitle=Proceedings%20of%208th%20Mediterranean%20Electrotechnical%20Conference%20on%20Industrial%20Applications%20in%20Power%20Systems,%20Computer%20Science%20and%20Telecommunications%20(MELECON%2096)&rft.au=Fathy,%20S.K.&rft.date=1996&rft.volume=3&rft.spage=1472&rft.epage=1475%20vol.3&rft.pages=1472-1475%20vol.3&rft.isbn=0780331095&rft.isbn_list=9780780331099&rft_id=info:doi/10.1109/MELCON.1996.551228&rft_dat=%3Cieee_6IE%3E551228%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=551228&rfr_iscdi=true