Optimal number of neurons for a two layer neural network model of a process
Neural networks are known as powerful tools to represent the essential properties of nonlinear processes because of their global approximation property. However, a key problem in modeling nonlinear processes by neural networks is the determination of neuron numbers. In this paper, a data based strat...
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 | 2221 |
|---|---|
| container_issue | |
| container_start_page | 2216 |
| container_title | |
| container_volume | |
| creator | Asadi, M. S. Fatehi, A. Hosseini, M. Sedigh, A. K. |
| description | Neural networks are known as powerful tools to represent the essential properties of nonlinear processes because of their global approximation property. However, a key problem in modeling nonlinear processes by neural networks is the determination of neuron numbers. In this paper, a data based strategy for determining number of hidden layer neurons based on the Barrons work, describing function analysis and bicoherence nonlinearity measure is proposed. The proposed algorithm is evaluated for a pH neutralization process. It is shown that this algorithm has acceptable results. |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6060341</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6060341</ieee_id><sourcerecordid>6060341</sourcerecordid><originalsourceid>FETCH-ieee_primary_60603413</originalsourceid><addsrcrecordid>eNp9jUEKwjAURCMiKNoTuPkXEFKaJs1aFMGFG_cl6i9U0yT8tEhvbyqunc0w8wZmxjKtKqG5UlIUupx_cy5KpbjKRbVkWYxPniRlAnrFzpfQt52x4IbuhgS-AYcDeReh8QQG-rcHa8aEpn4aYqroBZ1_oJ32BgL5O8a4YYvG2IjZz9dsezxc96ddi4h1oPRDYy255IXIi__0A_PKOsA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Optimal number of neurons for a two layer neural network model of a process</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Asadi, M. S. ; Fatehi, A. ; Hosseini, M. ; Sedigh, A. K.</creator><creatorcontrib>Asadi, M. S. ; Fatehi, A. ; Hosseini, M. ; Sedigh, A. K.</creatorcontrib><description>Neural networks are known as powerful tools to represent the essential properties of nonlinear processes because of their global approximation property. However, a key problem in modeling nonlinear processes by neural networks is the determination of neuron numbers. In this paper, a data based strategy for determining number of hidden layer neurons based on the Barrons work, describing function analysis and bicoherence nonlinearity measure is proposed. The proposed algorithm is evaluated for a pH neutralization process. It is shown that this algorithm has acceptable results.</description><identifier>ISBN: 9781457707148</identifier><identifier>ISBN: 1457707144</identifier><identifier>EISBN: 9784907764395</identifier><identifier>EISBN: 4907764391</identifier><identifier>EISBN: 9781907764388</identifier><language>eng</language><publisher>IEEE</publisher><subject>Approximation methods ; bicoherence test ; Biological neural networks ; Complexity theory ; Feedforward neural networks ; Frequency domain analysis ; Inphase-quadrature demodulation ; neural network ; Neurons ; Nonlinearity measure ; Training</subject><ispartof>SICE Annual Conference 2011, 2011, p.2216-2221</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/6060341$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6060341$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Asadi, M. S.</creatorcontrib><creatorcontrib>Fatehi, A.</creatorcontrib><creatorcontrib>Hosseini, M.</creatorcontrib><creatorcontrib>Sedigh, A. K.</creatorcontrib><title>Optimal number of neurons for a two layer neural network model of a process</title><title>SICE Annual Conference 2011</title><addtitle>SICE</addtitle><description>Neural networks are known as powerful tools to represent the essential properties of nonlinear processes because of their global approximation property. However, a key problem in modeling nonlinear processes by neural networks is the determination of neuron numbers. In this paper, a data based strategy for determining number of hidden layer neurons based on the Barrons work, describing function analysis and bicoherence nonlinearity measure is proposed. The proposed algorithm is evaluated for a pH neutralization process. It is shown that this algorithm has acceptable results.</description><subject>Approximation methods</subject><subject>bicoherence test</subject><subject>Biological neural networks</subject><subject>Complexity theory</subject><subject>Feedforward neural networks</subject><subject>Frequency domain analysis</subject><subject>Inphase-quadrature demodulation</subject><subject>neural network</subject><subject>Neurons</subject><subject>Nonlinearity measure</subject><subject>Training</subject><isbn>9781457707148</isbn><isbn>1457707144</isbn><isbn>9784907764395</isbn><isbn>4907764391</isbn><isbn>9781907764388</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9jUEKwjAURCMiKNoTuPkXEFKaJs1aFMGFG_cl6i9U0yT8tEhvbyqunc0w8wZmxjKtKqG5UlIUupx_cy5KpbjKRbVkWYxPniRlAnrFzpfQt52x4IbuhgS-AYcDeReh8QQG-rcHa8aEpn4aYqroBZ1_oJ32BgL5O8a4YYvG2IjZz9dsezxc96ddi4h1oPRDYy255IXIi__0A_PKOsA</recordid><startdate>201109</startdate><enddate>201109</enddate><creator>Asadi, M. S.</creator><creator>Fatehi, A.</creator><creator>Hosseini, M.</creator><creator>Sedigh, A. K.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201109</creationdate><title>Optimal number of neurons for a two layer neural network model of a process</title><author>Asadi, M. S. ; Fatehi, A. ; Hosseini, M. ; Sedigh, A. K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_60603413</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Approximation methods</topic><topic>bicoherence test</topic><topic>Biological neural networks</topic><topic>Complexity theory</topic><topic>Feedforward neural networks</topic><topic>Frequency domain analysis</topic><topic>Inphase-quadrature demodulation</topic><topic>neural network</topic><topic>Neurons</topic><topic>Nonlinearity measure</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Asadi, M. S.</creatorcontrib><creatorcontrib>Fatehi, A.</creatorcontrib><creatorcontrib>Hosseini, M.</creatorcontrib><creatorcontrib>Sedigh, A. K.</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>Asadi, M. S.</au><au>Fatehi, A.</au><au>Hosseini, M.</au><au>Sedigh, A. K.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Optimal number of neurons for a two layer neural network model of a process</atitle><btitle>SICE Annual Conference 2011</btitle><stitle>SICE</stitle><date>2011-09</date><risdate>2011</risdate><spage>2216</spage><epage>2221</epage><pages>2216-2221</pages><isbn>9781457707148</isbn><isbn>1457707144</isbn><eisbn>9784907764395</eisbn><eisbn>4907764391</eisbn><eisbn>9781907764388</eisbn><abstract>Neural networks are known as powerful tools to represent the essential properties of nonlinear processes because of their global approximation property. However, a key problem in modeling nonlinear processes by neural networks is the determination of neuron numbers. In this paper, a data based strategy for determining number of hidden layer neurons based on the Barrons work, describing function analysis and bicoherence nonlinearity measure is proposed. The proposed algorithm is evaluated for a pH neutralization process. It is shown that this algorithm has acceptable results.</abstract><pub>IEEE</pub></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9781457707148 |
| ispartof | SICE Annual Conference 2011, 2011, p.2216-2221 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_6060341 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Approximation methods bicoherence test Biological neural networks Complexity theory Feedforward neural networks Frequency domain analysis Inphase-quadrature demodulation neural network Neurons Nonlinearity measure Training |
| title | Optimal number of neurons for a two layer neural network model of a process |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T22%3A16%3A30IST&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=Optimal%20number%20of%20neurons%20for%20a%20two%20layer%20neural%20network%20model%20of%20a%20process&rft.btitle=SICE%20Annual%20Conference%202011&rft.au=Asadi,%20M.%20S.&rft.date=2011-09&rft.spage=2216&rft.epage=2221&rft.pages=2216-2221&rft.isbn=9781457707148&rft.isbn_list=1457707144&rft_id=info:doi/&rft_dat=%3Cieee_6IE%3E6060341%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9784907764395&rft.eisbn_list=4907764391&rft.eisbn_list=9781907764388&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6060341&rfr_iscdi=true |