A new feedback neural network with supervised learning

A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks 1991-01, Vol.2 (1), p.170-173
Main Authors: Salam, F.M.A., Bai, S.
Format: Article
Language:English
Subjects:
Artificial neural networks
Biological system modeling
Chaos
Exact sciences and technology
Feedforward neural networks
Function theory, analysis
Mathematical methods in physics
Neural networks
Neurofeedback
Neurons
Physics
Stability
State feedback
Supervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3
cites cdi_FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3
container_end_page 173
container_issue 1
container_start_page 170
container_title IEEE transactions on neural networks
container_volume 2
creator Salam, F.M.A.
Bai, S.
description A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium points. The modifications entail that the output signal of a neuron is multiplied by the square of its associated weight to supply the signal to an input of another neuron. A simulation of the complete dynamics is then presented for a prototype one neuron with self-feedback and supervised learning; the simulation illustrates the (supervised) learning capability of the network.< >
doi_str_mv 10.1109/72.80309
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_18276369</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>80309</ieee_id><sourcerecordid>734256041</sourcerecordid><originalsourceid>FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3</originalsourceid><addsrcrecordid>eNqF0DtPwzAQB3ALgWh5SKwsKAMClhS_H2NV8ZIqscAcOc4FQtOk2AkV3x5DqrLBdGfdT2f7j9AJwRNCsLlWdKIxw2YHjYnhJMXYsN3YYy5SQ6kaoYMQ3jAmXGC5j0ZEUyWZNGMkp0kD66QEKHLrFvHQe1vH0q1bv0jWVfeahH4F_qMKUCQ1WN9UzcsR2ittHeB4Uw_R8-3N0-w-nT_ePcym89QxbbqUas2NtPGNWjlaUKKYtU4ZZ6RUjFpe5tZKrUQef2EYUS4nkEPJOTaioCU7RJfD3pVv33sIXbasgoO6tg20fcgU41RIzEmUF39KqrlSmtD_oWDccMkivBqg820IHsps5aul9Z8Zwdl37Jmi2U_skZ5tdvb5EopfuMk5gvMNsMHZuvS2cVXYOkE55kZEdjqwCgC20-GOL8k0ju8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>25349463</pqid></control><display><type>article</type><title>A new feedback neural network with supervised learning</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Salam, F.M.A. ; Bai, S.</creator><creatorcontrib>Salam, F.M.A. ; Bai, S.</creatorcontrib><description>A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium points. The modifications entail that the output signal of a neuron is multiplied by the square of its associated weight to supply the signal to an input of another neuron. A simulation of the complete dynamics is then presented for a prototype one neuron with self-feedback and supervised learning; the simulation illustrates the (supervised) learning capability of the network.&lt; &gt;</description><identifier>ISSN: 1045-9227</identifier><identifier>EISSN: 1941-0093</identifier><identifier>DOI: 10.1109/72.80309</identifier><identifier>PMID: 18276369</identifier><identifier>CODEN: ITNNEP</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Artificial neural networks ; Biological system modeling ; Chaos ; Exact sciences and technology ; Feedforward neural networks ; Function theory, analysis ; Mathematical methods in physics ; Neural networks ; Neurofeedback ; Neurons ; Physics ; Stability ; State feedback ; Supervised learning</subject><ispartof>IEEE transactions on neural networks, 1991-01, Vol.2 (1), p.170-173</ispartof><rights>1992 INIST-CNRS</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3</citedby><cites>FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/80309$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,4024,27923,27924,27925,54796</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=5240495$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18276369$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Salam, F.M.A.</creatorcontrib><creatorcontrib>Bai, S.</creatorcontrib><title>A new feedback neural network with supervised learning</title><title>IEEE transactions on neural networks</title><addtitle>TNN</addtitle><addtitle>IEEE Trans Neural Netw</addtitle><description>A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium points. The modifications entail that the output signal of a neuron is multiplied by the square of its associated weight to supply the signal to an input of another neuron. A simulation of the complete dynamics is then presented for a prototype one neuron with self-feedback and supervised learning; the simulation illustrates the (supervised) learning capability of the network.&lt; &gt;</description><subject>Artificial neural networks</subject><subject>Biological system modeling</subject><subject>Chaos</subject><subject>Exact sciences and technology</subject><subject>Feedforward neural networks</subject><subject>Function theory, analysis</subject><subject>Mathematical methods in physics</subject><subject>Neural networks</subject><subject>Neurofeedback</subject><subject>Neurons</subject><subject>Physics</subject><subject>Stability</subject><subject>State feedback</subject><subject>Supervised learning</subject><issn>1045-9227</issn><issn>1941-0093</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1991</creationdate><recordtype>article</recordtype><recordid>eNqF0DtPwzAQB3ALgWh5SKwsKAMClhS_H2NV8ZIqscAcOc4FQtOk2AkV3x5DqrLBdGfdT2f7j9AJwRNCsLlWdKIxw2YHjYnhJMXYsN3YYy5SQ6kaoYMQ3jAmXGC5j0ZEUyWZNGMkp0kD66QEKHLrFvHQe1vH0q1bv0jWVfeahH4F_qMKUCQ1WN9UzcsR2ittHeB4Uw_R8-3N0-w-nT_ePcym89QxbbqUas2NtPGNWjlaUKKYtU4ZZ6RUjFpe5tZKrUQef2EYUS4nkEPJOTaioCU7RJfD3pVv33sIXbasgoO6tg20fcgU41RIzEmUF39KqrlSmtD_oWDccMkivBqg820IHsps5aul9Z8Zwdl37Jmi2U_skZ5tdvb5EopfuMk5gvMNsMHZuvS2cVXYOkE55kZEdjqwCgC20-GOL8k0ju8</recordid><startdate>199101</startdate><enddate>199101</enddate><creator>Salam, F.M.A.</creator><creator>Bai, S.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><scope>IQODW</scope><scope>NPM</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><scope>7X8</scope></search><sort><creationdate>199101</creationdate><title>A new feedback neural network with supervised learning</title><author>Salam, F.M.A. ; Bai, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1991</creationdate><topic>Artificial neural networks</topic><topic>Biological system modeling</topic><topic>Chaos</topic><topic>Exact sciences and technology</topic><topic>Feedforward neural networks</topic><topic>Function theory, analysis</topic><topic>Mathematical methods in physics</topic><topic>Neural networks</topic><topic>Neurofeedback</topic><topic>Neurons</topic><topic>Physics</topic><topic>Stability</topic><topic>State feedback</topic><topic>Supervised learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Salam, F.M.A.</creatorcontrib><creatorcontrib>Bai, S.</creatorcontrib><collection>Pascal-Francis</collection><collection>PubMed</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><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Salam, F.M.A.</au><au>Bai, S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A new feedback neural network with supervised learning</atitle><jtitle>IEEE transactions on neural networks</jtitle><stitle>TNN</stitle><addtitle>IEEE Trans Neural Netw</addtitle><date>1991-01</date><risdate>1991</risdate><volume>2</volume><issue>1</issue><spage>170</spage><epage>173</epage><pages>170-173</pages><issn>1045-9227</issn><eissn>1941-0093</eissn><coden>ITNNEP</coden><abstract>A model is introduced for continuous-time dynamic feedback neural networks with supervised learning ability. Modifications are introduced to conventional models to guarantee precisely that a given desired vector, and its negative, are indeed stored in the network as asymptotically stable equilibrium points. The modifications entail that the output signal of a neuron is multiplied by the square of its associated weight to supply the signal to an input of another neuron. A simulation of the complete dynamics is then presented for a prototype one neuron with self-feedback and supervised learning; the simulation illustrates the (supervised) learning capability of the network.&lt; &gt;</abstract><cop>New York, NY</cop><pub>IEEE</pub><pmid>18276369</pmid><doi>10.1109/72.80309</doi><tpages>4</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1045-9227
ispartof IEEE transactions on neural networks, 1991-01, Vol.2 (1), p.170-173
issn 1045-9227
1941-0093
language eng
recordid cdi_pubmed_primary_18276369
source IEEE Electronic Library (IEL) Journals
subjects Artificial neural networks
Biological system modeling
Chaos
Exact sciences and technology
Feedforward neural networks
Function theory, analysis
Mathematical methods in physics
Neural networks
Neurofeedback
Neurons
Physics
Stability
State feedback
Supervised learning
title A new feedback neural network with supervised learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T23%3A58%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20new%20feedback%20neural%20network%20with%20supervised%20learning&rft.jtitle=IEEE%20transactions%20on%20neural%20networks&rft.au=Salam,%20F.M.A.&rft.date=1991-01&rft.volume=2&rft.issue=1&rft.spage=170&rft.epage=173&rft.pages=170-173&rft.issn=1045-9227&rft.eissn=1941-0093&rft.coden=ITNNEP&rft_id=info:doi/10.1109/72.80309&rft_dat=%3Cproquest_pubme%3E734256041%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c389t-288496a11087c2d2173aac79c966732a4fbaa6875b1099317cb1ebef44095d2f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=25349463&rft_id=info:pmid/18276369&rft_ieee_id=80309&rfr_iscdi=true