Embedding Theoretical Models in Neural Networks
A novel method for incorporating constraints and default models into neural networks is presented. The method involves a parallel arrangement of a default model and a radial basis function network. The training procedure accounts for equality and inequality constraints that must be satisfied for all...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 479 |
|---|---|
| container_issue | |
| container_start_page | 475 |
| container_title | |
| container_volume | |
| creator | Kramer, Mark A. Thompson, Michael L. Bhagat, Phiroz M. |
| description | A novel method for incorporating constraints and default models into neural networks is presented. The method involves a parallel arrangement of a default model and a radial basis function network. The training procedure accounts for equality and inequality constraints that must be satisfied for all future inputs to the network. In the case of linear equality constraints and no inequality constraints, training is reduced to a quadratic problem possessing an analytical solution. The extrapolation properties of the model-based network are controllable to a greater extent than previous network models. |
| doi_str_mv | 10.23919/ACC.1992.4792111 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4792111</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4792111</ieee_id><sourcerecordid>4792111</sourcerecordid><originalsourceid>FETCH-LOGICAL-c136t-44245fce2091cad14c732b52e7c655fd34502de53cad447e72dbd1f35f4d93fb3</originalsourceid><addsrcrecordid>eNotj81qwzAQhAUlkDbNA4Re_AJ2tLtSZB2DSX8gTS_JOdjSqlXrxEV2KX37GpK5DHwDH4wQC5AFkgW7XFdVAdZioYxFALgRd9KUkiSCtBMxtZDrErCcinnff8oxWhur5K1Ybk4Nex_P79n-g7vEQ3R1m712nts-i-dsxz9pBDsefrv01d-LSajbnufXnonD42ZfPefbt6eXar3NHdBqyJVCpYNjlBZc7UE5Q9hoZONWWgdPSkv0rGkclTJs0DceAumgvKXQ0Ew8XLyRmY_fKZ7q9He83qN_0EVC2w</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Embedding Theoretical Models in Neural Networks</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kramer, Mark A. ; Thompson, Michael L. ; Bhagat, Phiroz M.</creator><creatorcontrib>Kramer, Mark A. ; Thompson, Michael L. ; Bhagat, Phiroz M.</creatorcontrib><description>A novel method for incorporating constraints and default models into neural networks is presented. The method involves a parallel arrangement of a default model and a radial basis function network. The training procedure accounts for equality and inequality constraints that must be satisfied for all future inputs to the network. In the case of linear equality constraints and no inequality constraints, training is reduced to a quadratic problem possessing an analytical solution. The extrapolation properties of the model-based network are controllable to a greater extent than previous network models.</description><identifier>ISBN: 0780302109</identifier><identifier>ISBN: 9780780302105</identifier><identifier>DOI: 10.23919/ACC.1992.4792111</identifier><identifier>LCCN: 91-58128</identifier><language>eng</language><publisher>IEEE</publisher><subject>Backpropagation ; Bioreactors ; Constraint theory ; Context modeling ; Extrapolation ; Intelligent networks ; Neural networks ; Nonlinear systems ; Parameter estimation ; Predictive models</subject><ispartof>1992 American Control Conference, 1992, p.475-479</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c136t-44245fce2091cad14c732b52e7c655fd34502de53cad447e72dbd1f35f4d93fb3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4792111$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4792111$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kramer, Mark A.</creatorcontrib><creatorcontrib>Thompson, Michael L.</creatorcontrib><creatorcontrib>Bhagat, Phiroz M.</creatorcontrib><title>Embedding Theoretical Models in Neural Networks</title><title>1992 American Control Conference</title><addtitle>ACC</addtitle><description>A novel method for incorporating constraints and default models into neural networks is presented. The method involves a parallel arrangement of a default model and a radial basis function network. The training procedure accounts for equality and inequality constraints that must be satisfied for all future inputs to the network. In the case of linear equality constraints and no inequality constraints, training is reduced to a quadratic problem possessing an analytical solution. The extrapolation properties of the model-based network are controllable to a greater extent than previous network models.</description><subject>Backpropagation</subject><subject>Bioreactors</subject><subject>Constraint theory</subject><subject>Context modeling</subject><subject>Extrapolation</subject><subject>Intelligent networks</subject><subject>Neural networks</subject><subject>Nonlinear systems</subject><subject>Parameter estimation</subject><subject>Predictive models</subject><isbn>0780302109</isbn><isbn>9780780302105</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1992</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj81qwzAQhAUlkDbNA4Re_AJ2tLtSZB2DSX8gTS_JOdjSqlXrxEV2KX37GpK5DHwDH4wQC5AFkgW7XFdVAdZioYxFALgRd9KUkiSCtBMxtZDrErCcinnff8oxWhur5K1Ybk4Nex_P79n-g7vEQ3R1m712nts-i-dsxz9pBDsefrv01d-LSajbnufXnonD42ZfPefbt6eXar3NHdBqyJVCpYNjlBZc7UE5Q9hoZONWWgdPSkv0rGkclTJs0DceAumgvKXQ0Ew8XLyRmY_fKZ7q9He83qN_0EVC2w</recordid><startdate>199206</startdate><enddate>199206</enddate><creator>Kramer, Mark A.</creator><creator>Thompson, Michael L.</creator><creator>Bhagat, Phiroz M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>199206</creationdate><title>Embedding Theoretical Models in Neural Networks</title><author>Kramer, Mark A. ; Thompson, Michael L. ; Bhagat, Phiroz M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c136t-44245fce2091cad14c732b52e7c655fd34502de53cad447e72dbd1f35f4d93fb3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1992</creationdate><topic>Backpropagation</topic><topic>Bioreactors</topic><topic>Constraint theory</topic><topic>Context modeling</topic><topic>Extrapolation</topic><topic>Intelligent networks</topic><topic>Neural networks</topic><topic>Nonlinear systems</topic><topic>Parameter estimation</topic><topic>Predictive models</topic><toplevel>online_resources</toplevel><creatorcontrib>Kramer, Mark A.</creatorcontrib><creatorcontrib>Thompson, Michael L.</creatorcontrib><creatorcontrib>Bhagat, Phiroz 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 Xplore (Online service)</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>Kramer, Mark A.</au><au>Thompson, Michael L.</au><au>Bhagat, Phiroz M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Embedding Theoretical Models in Neural Networks</atitle><btitle>1992 American Control Conference</btitle><stitle>ACC</stitle><date>1992-06</date><risdate>1992</risdate><spage>475</spage><epage>479</epage><pages>475-479</pages><isbn>0780302109</isbn><isbn>9780780302105</isbn><abstract>A novel method for incorporating constraints and default models into neural networks is presented. The method involves a parallel arrangement of a default model and a radial basis function network. The training procedure accounts for equality and inequality constraints that must be satisfied for all future inputs to the network. In the case of linear equality constraints and no inequality constraints, training is reduced to a quadratic problem possessing an analytical solution. The extrapolation properties of the model-based network are controllable to a greater extent than previous network models.</abstract><pub>IEEE</pub><doi>10.23919/ACC.1992.4792111</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780302109 |
| ispartof | 1992 American Control Conference, 1992, p.475-479 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_4792111 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Backpropagation Bioreactors Constraint theory Context modeling Extrapolation Intelligent networks Neural networks Nonlinear systems Parameter estimation Predictive models |
| title | Embedding Theoretical Models in Neural Networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T18%3A34%3A03IST&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=Embedding%20Theoretical%20Models%20in%20Neural%20Networks&rft.btitle=1992%20American%20Control%20Conference&rft.au=Kramer,%20Mark%20A.&rft.date=1992-06&rft.spage=475&rft.epage=479&rft.pages=475-479&rft.isbn=0780302109&rft.isbn_list=9780780302105&rft_id=info:doi/10.23919/ACC.1992.4792111&rft_dat=%3Cieee_6IE%3E4792111%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=4792111&rfr_iscdi=true |