Genetic algorithm optimize neural network based on structural risk minimization
The paper demonstrates a method for optimizing a neural network based on structural risk minimization (SRM). The method combines the principle of SRM and neural network using genetic algorithms to optimize the perceptron to avoid the failings of the traditional perceptron; local convergence of conne...
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 | 952 vol.2 |
|---|---|
| container_issue | |
| container_start_page | 948 |
| container_title | |
| container_volume | 2 |
| creator | Fan Jinsong Tao Qing Fang Tingjian |
| description | The paper demonstrates a method for optimizing a neural network based on structural risk minimization (SRM). The method combines the principle of SRM and neural network using genetic algorithms to optimize the perceptron to avoid the failings of the traditional perceptron; local convergence of connection weight and high probability of failed recognition. Owing to global optimization by the genetic algorithm, the improved method can evolve and adapt itself. It has better generalization performance and better property of avoiding disturbance, which improves the whole performance of the neural network. Compared with the normal algorithm of SVM, it has wide application and strong ability to deal with large data. |
| doi_str_mv | 10.1109/WCICA.2000.863373 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_863373</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>863373</ieee_id><sourcerecordid>863373</sourcerecordid><originalsourceid>FETCH-ieee_primary_8633733</originalsourceid><addsrcrecordid>eNp9zrsOgjAYhuEmxsQTF6BTb0AsFARGQzxNLia6kYq_-gu0pC0xevUeZ6d3ePIlHyFDj7mex5LJLl2nM9dnjLnxlPOIt0iPRTHjYZKE-w5xjLm-kAUB54nfJZslSLCYU1GelUZ7qaiqLVb4ACqh0aJ8xd6ULuhBGDhSJamxusntxzSaglYo3wNhUckBaZ9EacD5tU9Gi_k2XY0RALJaYyX0Pfte43_xCbsAP1Q</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Genetic algorithm optimize neural network based on structural risk minimization</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Fan Jinsong ; Tao Qing ; Fang Tingjian</creator><creatorcontrib>Fan Jinsong ; Tao Qing ; Fang Tingjian</creatorcontrib><description>The paper demonstrates a method for optimizing a neural network based on structural risk minimization (SRM). The method combines the principle of SRM and neural network using genetic algorithms to optimize the perceptron to avoid the failings of the traditional perceptron; local convergence of connection weight and high probability of failed recognition. Owing to global optimization by the genetic algorithm, the improved method can evolve and adapt itself. It has better generalization performance and better property of avoiding disturbance, which improves the whole performance of the neural network. Compared with the normal algorithm of SVM, it has wide application and strong ability to deal with large data.</description><identifier>ISBN: 078035995X</identifier><identifier>ISBN: 9780780359956</identifier><identifier>DOI: 10.1109/WCICA.2000.863373</identifier><language>eng</language><publisher>IEEE</publisher><subject>Convergence ; Genetic algorithms ; Intelligent networks ; Intelligent structures ; Machine intelligence ; Neural networks ; Optimization methods ; Paper technology ; Risk management ; Support vector machines</subject><ispartof>Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393), 2000, Vol.2, p.948-952 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/863373$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,4036,4037,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/863373$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Fan Jinsong</creatorcontrib><creatorcontrib>Tao Qing</creatorcontrib><creatorcontrib>Fang Tingjian</creatorcontrib><title>Genetic algorithm optimize neural network based on structural risk minimization</title><title>Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393)</title><addtitle>WCICA</addtitle><description>The paper demonstrates a method for optimizing a neural network based on structural risk minimization (SRM). The method combines the principle of SRM and neural network using genetic algorithms to optimize the perceptron to avoid the failings of the traditional perceptron; local convergence of connection weight and high probability of failed recognition. Owing to global optimization by the genetic algorithm, the improved method can evolve and adapt itself. It has better generalization performance and better property of avoiding disturbance, which improves the whole performance of the neural network. Compared with the normal algorithm of SVM, it has wide application and strong ability to deal with large data.</description><subject>Convergence</subject><subject>Genetic algorithms</subject><subject>Intelligent networks</subject><subject>Intelligent structures</subject><subject>Machine intelligence</subject><subject>Neural networks</subject><subject>Optimization methods</subject><subject>Paper technology</subject><subject>Risk management</subject><subject>Support vector machines</subject><isbn>078035995X</isbn><isbn>9780780359956</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2000</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9zrsOgjAYhuEmxsQTF6BTb0AsFARGQzxNLia6kYq_-gu0pC0xevUeZ6d3ePIlHyFDj7mex5LJLl2nM9dnjLnxlPOIt0iPRTHjYZKE-w5xjLm-kAUB54nfJZslSLCYU1GelUZ7qaiqLVb4ACqh0aJ8xd6ULuhBGDhSJamxusntxzSaglYo3wNhUckBaZ9EacD5tU9Gi_k2XY0RALJaYyX0Pfte43_xCbsAP1Q</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Fan Jinsong</creator><creator>Tao Qing</creator><creator>Fang Tingjian</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2000</creationdate><title>Genetic algorithm optimize neural network based on structural risk minimization</title><author>Fan Jinsong ; Tao Qing ; Fang Tingjian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_8633733</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Convergence</topic><topic>Genetic algorithms</topic><topic>Intelligent networks</topic><topic>Intelligent structures</topic><topic>Machine intelligence</topic><topic>Neural networks</topic><topic>Optimization methods</topic><topic>Paper technology</topic><topic>Risk management</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Fan Jinsong</creatorcontrib><creatorcontrib>Tao Qing</creatorcontrib><creatorcontrib>Fang Tingjian</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>Fan Jinsong</au><au>Tao Qing</au><au>Fang Tingjian</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Genetic algorithm optimize neural network based on structural risk minimization</atitle><btitle>Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393)</btitle><stitle>WCICA</stitle><date>2000</date><risdate>2000</risdate><volume>2</volume><spage>948</spage><epage>952 vol.2</epage><pages>948-952 vol.2</pages><isbn>078035995X</isbn><isbn>9780780359956</isbn><abstract>The paper demonstrates a method for optimizing a neural network based on structural risk minimization (SRM). The method combines the principle of SRM and neural network using genetic algorithms to optimize the perceptron to avoid the failings of the traditional perceptron; local convergence of connection weight and high probability of failed recognition. Owing to global optimization by the genetic algorithm, the improved method can evolve and adapt itself. It has better generalization performance and better property of avoiding disturbance, which improves the whole performance of the neural network. Compared with the normal algorithm of SVM, it has wide application and strong ability to deal with large data.</abstract><pub>IEEE</pub><doi>10.1109/WCICA.2000.863373</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 078035995X |
| ispartof | Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393), 2000, Vol.2, p.948-952 vol.2 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_863373 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Convergence Genetic algorithms Intelligent networks Intelligent structures Machine intelligence Neural networks Optimization methods Paper technology Risk management Support vector machines |
| title | Genetic algorithm optimize neural network based on structural risk minimization |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T01%3A21%3A05IST&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=Genetic%20algorithm%20optimize%20neural%20network%20based%20on%20structural%20risk%20minimization&rft.btitle=Proceedings%20of%20the%203rd%20World%20Congress%20on%20Intelligent%20Control%20and%20Automation%20(Cat.%20No.00EX393)&rft.au=Fan%20Jinsong&rft.date=2000&rft.volume=2&rft.spage=948&rft.epage=952%20vol.2&rft.pages=948-952%20vol.2&rft.isbn=078035995X&rft.isbn_list=9780780359956&rft_id=info:doi/10.1109/WCICA.2000.863373&rft_dat=%3Cieee_6IE%3E863373%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=863373&rfr_iscdi=true |