Back propagation with expected source values
The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative...
Gespeichert in:
| Veröffentlicht in: | Neural networks 1991, Vol.4 (5), p.615-618 |
|---|---|
| 1. Verfasser: | |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 618 |
|---|---|
| container_issue | 5 |
| container_start_page | 615 |
| container_title | Neural networks |
| container_volume | 4 |
| creator | Samad, Tariq |
| description | The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule. |
| doi_str_mv | 10.1016/0893-6080(91)90015-W |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_25113687</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>089360809190015W</els_id><sourcerecordid>25113687</sourcerecordid><originalsourceid>FETCH-LOGICAL-c364t-8c72f4ccfb1d3c142b2e392c3dbbe0120c8ae36e011a15867fd9cd6bc520e74a3</originalsourceid><addsrcrecordid>eNp9kEtPwzAQhC0EEqXwDzjkgBBIBPxIHPuCBBUvqRIXUI-Ws9mAIU2CnRb497i04shp9_DN7M4QcsjoOaNMXlClRSqpoieanWpKWZ7OtsiIqUKnvFB8m4z-kF2yF8IbpVSqTIzI2bWF96T3XW9f7OC6Nvl0w2uCXz3CgFUSuoUHTJa2WWDYJzu1bQIebOaYPN_ePE3u0-nj3cPkapqCkNmQKih4nQHUJasEsIyXHIXmIKqyRMo4BWVRyLgyy3Ili7rSUMkSck6xyKwYk-O1b_zrI94dzNwFwKaxLXaLYHjOmJCqiGC2BsF3IXisTe_d3Ppvw6hZVWNWuc0qt9HM_FZjZlF2tPG3AWxTe9uCC3_a6M60ziJ2ucYwZl069CaAwxawcj62Y6rO_X_nB3Ktd1E</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>25113687</pqid></control><display><type>article</type><title>Back propagation with expected source values</title><source>Elsevier ScienceDirect Journals</source><creator>Samad, Tariq</creator><creatorcontrib>Samad, Tariq</creatorcontrib><description>The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/0893-6080(91)90015-W</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Applied sciences ; Artificial intelligence ; Back propagation ; Computer science; control theory; systems ; Connectionism. Neural networks ; Exact sciences and technology ; Neural networks ; Supervised learning</subject><ispartof>Neural networks, 1991, Vol.4 (5), p.615-618</ispartof><rights>1991</rights><rights>1992 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c364t-8c72f4ccfb1d3c142b2e392c3dbbe0120c8ae36e011a15867fd9cd6bc520e74a3</citedby><cites>FETCH-LOGICAL-c364t-8c72f4ccfb1d3c142b2e392c3dbbe0120c8ae36e011a15867fd9cd6bc520e74a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/089360809190015W$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3536,4009,27902,27903,27904,65309</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=5111994$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Samad, Tariq</creatorcontrib><title>Back propagation with expected source values</title><title>Neural networks</title><description>The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Back propagation</subject><subject>Computer science; control theory; systems</subject><subject>Connectionism. Neural networks</subject><subject>Exact sciences and technology</subject><subject>Neural networks</subject><subject>Supervised learning</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1991</creationdate><recordtype>article</recordtype><recordid>eNp9kEtPwzAQhC0EEqXwDzjkgBBIBPxIHPuCBBUvqRIXUI-Ws9mAIU2CnRb497i04shp9_DN7M4QcsjoOaNMXlClRSqpoieanWpKWZ7OtsiIqUKnvFB8m4z-kF2yF8IbpVSqTIzI2bWF96T3XW9f7OC6Nvl0w2uCXz3CgFUSuoUHTJa2WWDYJzu1bQIebOaYPN_ePE3u0-nj3cPkapqCkNmQKih4nQHUJasEsIyXHIXmIKqyRMo4BWVRyLgyy3Ili7rSUMkSck6xyKwYk-O1b_zrI94dzNwFwKaxLXaLYHjOmJCqiGC2BsF3IXisTe_d3Ppvw6hZVWNWuc0qt9HM_FZjZlF2tPG3AWxTe9uCC3_a6M60ziJ2ucYwZl069CaAwxawcj62Y6rO_X_nB3Ktd1E</recordid><startdate>1991</startdate><enddate>1991</enddate><creator>Samad, Tariq</creator><general>Elsevier Ltd</general><general>Elsevier Science</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>1991</creationdate><title>Back propagation with expected source values</title><author>Samad, Tariq</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c364t-8c72f4ccfb1d3c142b2e392c3dbbe0120c8ae36e011a15867fd9cd6bc520e74a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1991</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Back propagation</topic><topic>Computer science; control theory; systems</topic><topic>Connectionism. Neural networks</topic><topic>Exact sciences and technology</topic><topic>Neural networks</topic><topic>Supervised learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Samad, Tariq</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Samad, Tariq</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Back propagation with expected source values</atitle><jtitle>Neural networks</jtitle><date>1991</date><risdate>1991</risdate><volume>4</volume><issue>5</issue><spage>615</spage><epage>618</epage><pages>615-618</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><abstract>The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><doi>10.1016/0893-6080(91)90015-W</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0893-6080 |
| ispartof | Neural networks, 1991, Vol.4 (5), p.615-618 |
| issn | 0893-6080 1879-2782 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_25113687 |
| source | Elsevier ScienceDirect Journals |
| subjects | Applied sciences Artificial intelligence Back propagation Computer science control theory systems Connectionism. Neural networks Exact sciences and technology Neural networks Supervised learning |
| title | Back propagation with expected source values |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T17%3A16%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Back%20propagation%20with%20expected%20source%20values&rft.jtitle=Neural%20networks&rft.au=Samad,%20Tariq&rft.date=1991&rft.volume=4&rft.issue=5&rft.spage=615&rft.epage=618&rft.pages=615-618&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/0893-6080(91)90015-W&rft_dat=%3Cproquest_cross%3E25113687%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=25113687&rft_id=info:pmid/&rft_els_id=089360809190015W&rfr_iscdi=true |