Adaptive competitive self-organizing associative memory
This work presents the design of an adaptive competitive self-organizing associative memory (ACSAM) system for use in classification and recognition of pattern information. Volterra and Lotka's models of interacting species in biology motivated the ACSAM model; a model based on a system of nonl...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on systems, man and cybernetics. Part A, Systems and humans man and cybernetics. Part A, Systems and humans, 2002-07, Vol.32 (4), p.461-471 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 471 |
|---|---|
| container_issue | 4 |
| container_start_page | 461 |
| container_title | IEEE transactions on systems, man and cybernetics. Part A, Systems and humans |
| container_volume | 32 |
| creator | Athinarayanan, R. Sayeh, M.R. Wood, D.A. |
| description | This work presents the design of an adaptive competitive self-organizing associative memory (ACSAM) system for use in classification and recognition of pattern information. Volterra and Lotka's models of interacting species in biology motivated the ACSAM model; a model based on a system of nonlinear ordinary differential equations (ODEs). Self-organizing behavior is modeled for unsupervised neural networks employing the concept of interacting/competing species in biology. In this model, self-organizing properties can be implicitly coded within the systems trajectory structure using only ODEs. Among the features of this continuous-time system are: 1) the dynamic behavior is well-understood and characterized; 2) the desired fixed points are the only asymptotically stable states of the system; 3) the trajectories of ACSAM derived from the weight activities of the gradient system have no periodic or homoclinic orbits; and 4) the heteroclinic orbits that exist between equilibrium states are structurally unstable and can be removed by small perturbations. |
| doi_str_mv | 10.1109/TSMCA.2002.804789 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_28913774</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1158963</ieee_id><sourcerecordid>28202520</sourcerecordid><originalsourceid>FETCH-LOGICAL-c384t-ced24b61b21d113bf382b069223e456cce979067ee51e93f806bc96ebe27bd3e3</originalsourceid><addsrcrecordid>eNqNkU1LAzEQhoMoWKs_QLwUD3ramkySTXIsxS9QPFjPYTc7W7bsbmqyFeqvd9sVBA_iaV6YZwZmHkLOGZ0yRs3N4vV5PpsCpTDVVChtDsiISakTEJAe9plqnggB6picxLiilAlhxIioWZGtu-oDJ843a-yqfY5Yl4kPy6ytPqt2Ocli9K7K9r0GGx-2p-SozOqIZ991TN7ubhfzh-Tp5f5xPntKHNeiSxwWIPKU5cAKxnhecg05TQ0ARyFT59AoQ1OFKBkaXmqa5s6kmCOovODIx-R62LsO_n2DsbNNFR3Wddai30RrqDKSMwk9efUnCdowrpT4BwgUJNAevPwFrvwmtP25Vuv-fRKk7CE2QC74GAOWdh2qJgtby6jdqbF7NXanxg5q-pmLYaZCxB-eSW1Szr8Ae9SJeA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>884495255</pqid></control><display><type>article</type><title>Adaptive competitive self-organizing associative memory</title><source>IEEE Electronic Library (IEL)</source><creator>Athinarayanan, R. ; Sayeh, M.R. ; Wood, D.A.</creator><creatorcontrib>Athinarayanan, R. ; Sayeh, M.R. ; Wood, D.A.</creatorcontrib><description>This work presents the design of an adaptive competitive self-organizing associative memory (ACSAM) system for use in classification and recognition of pattern information. Volterra and Lotka's models of interacting species in biology motivated the ACSAM model; a model based on a system of nonlinear ordinary differential equations (ODEs). Self-organizing behavior is modeled for unsupervised neural networks employing the concept of interacting/competing species in biology. In this model, self-organizing properties can be implicitly coded within the systems trajectory structure using only ODEs. Among the features of this continuous-time system are: 1) the dynamic behavior is well-understood and characterized; 2) the desired fixed points are the only asymptotically stable states of the system; 3) the trajectories of ACSAM derived from the weight activities of the gradient system have no periodic or homoclinic orbits; and 4) the heteroclinic orbits that exist between equilibrium states are structurally unstable and can be removed by small perturbations.</description><identifier>ISSN: 1083-4427</identifier><identifier>ISSN: 2168-2216</identifier><identifier>EISSN: 1558-2426</identifier><identifier>EISSN: 2168-2232</identifier><identifier>DOI: 10.1109/TSMCA.2002.804789</identifier><identifier>CODEN: ITSHFX</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Associative memory ; Asymptotic properties ; Biological system modeling ; Biology ; Clustering algorithms ; Computational biology ; Differential equations ; Dynamical systems ; Dynamics ; Neural networks ; Neurons ; Nonlinear dynamics ; Orbits ; Ordinary differential equations ; Pattern recognition ; Prototypes ; Studies ; Trajectories</subject><ispartof>IEEE transactions on systems, man and cybernetics. Part A, Systems and humans, 2002-07, Vol.32 (4), p.461-471</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2002</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c384t-ced24b61b21d113bf382b069223e456cce979067ee51e93f806bc96ebe27bd3e3</citedby><cites>FETCH-LOGICAL-c384t-ced24b61b21d113bf382b069223e456cce979067ee51e93f806bc96ebe27bd3e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1158963$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1158963$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Athinarayanan, R.</creatorcontrib><creatorcontrib>Sayeh, M.R.</creatorcontrib><creatorcontrib>Wood, D.A.</creatorcontrib><title>Adaptive competitive self-organizing associative memory</title><title>IEEE transactions on systems, man and cybernetics. Part A, Systems and humans</title><addtitle>TSMCA</addtitle><description>This work presents the design of an adaptive competitive self-organizing associative memory (ACSAM) system for use in classification and recognition of pattern information. Volterra and Lotka's models of interacting species in biology motivated the ACSAM model; a model based on a system of nonlinear ordinary differential equations (ODEs). Self-organizing behavior is modeled for unsupervised neural networks employing the concept of interacting/competing species in biology. In this model, self-organizing properties can be implicitly coded within the systems trajectory structure using only ODEs. Among the features of this continuous-time system are: 1) the dynamic behavior is well-understood and characterized; 2) the desired fixed points are the only asymptotically stable states of the system; 3) the trajectories of ACSAM derived from the weight activities of the gradient system have no periodic or homoclinic orbits; and 4) the heteroclinic orbits that exist between equilibrium states are structurally unstable and can be removed by small perturbations.</description><subject>Algorithms</subject><subject>Associative memory</subject><subject>Asymptotic properties</subject><subject>Biological system modeling</subject><subject>Biology</subject><subject>Clustering algorithms</subject><subject>Computational biology</subject><subject>Differential equations</subject><subject>Dynamical systems</subject><subject>Dynamics</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Nonlinear dynamics</subject><subject>Orbits</subject><subject>Ordinary differential equations</subject><subject>Pattern recognition</subject><subject>Prototypes</subject><subject>Studies</subject><subject>Trajectories</subject><issn>1083-4427</issn><issn>2168-2216</issn><issn>1558-2426</issn><issn>2168-2232</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2002</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNqNkU1LAzEQhoMoWKs_QLwUD3ramkySTXIsxS9QPFjPYTc7W7bsbmqyFeqvd9sVBA_iaV6YZwZmHkLOGZ0yRs3N4vV5PpsCpTDVVChtDsiISakTEJAe9plqnggB6picxLiilAlhxIioWZGtu-oDJ843a-yqfY5Yl4kPy6ytPqt2Ocli9K7K9r0GGx-2p-SozOqIZ991TN7ubhfzh-Tp5f5xPntKHNeiSxwWIPKU5cAKxnhecg05TQ0ARyFT59AoQ1OFKBkaXmqa5s6kmCOovODIx-R62LsO_n2DsbNNFR3Wddai30RrqDKSMwk9efUnCdowrpT4BwgUJNAevPwFrvwmtP25Vuv-fRKk7CE2QC74GAOWdh2qJgtby6jdqbF7NXanxg5q-pmLYaZCxB-eSW1Szr8Ae9SJeA</recordid><startdate>20020701</startdate><enddate>20020701</enddate><creator>Athinarayanan, R.</creator><creator>Sayeh, M.R.</creator><creator>Wood, D.A.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope></search><sort><creationdate>20020701</creationdate><title>Adaptive competitive self-organizing associative memory</title><author>Athinarayanan, R. ; Sayeh, M.R. ; Wood, D.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c384t-ced24b61b21d113bf382b069223e456cce979067ee51e93f806bc96ebe27bd3e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Algorithms</topic><topic>Associative memory</topic><topic>Asymptotic properties</topic><topic>Biological system modeling</topic><topic>Biology</topic><topic>Clustering algorithms</topic><topic>Computational biology</topic><topic>Differential equations</topic><topic>Dynamical systems</topic><topic>Dynamics</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Nonlinear dynamics</topic><topic>Orbits</topic><topic>Ordinary differential equations</topic><topic>Pattern recognition</topic><topic>Prototypes</topic><topic>Studies</topic><topic>Trajectories</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Athinarayanan, R.</creatorcontrib><creatorcontrib>Sayeh, M.R.</creatorcontrib><creatorcontrib>Wood, D.A.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace 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>ANTE: Abstracts in New Technology & Engineering</collection><jtitle>IEEE transactions on systems, man and cybernetics. Part A, Systems and humans</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Athinarayanan, R.</au><au>Sayeh, M.R.</au><au>Wood, D.A.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adaptive competitive self-organizing associative memory</atitle><jtitle>IEEE transactions on systems, man and cybernetics. Part A, Systems and humans</jtitle><stitle>TSMCA</stitle><date>2002-07-01</date><risdate>2002</risdate><volume>32</volume><issue>4</issue><spage>461</spage><epage>471</epage><pages>461-471</pages><issn>1083-4427</issn><issn>2168-2216</issn><eissn>1558-2426</eissn><eissn>2168-2232</eissn><coden>ITSHFX</coden><abstract>This work presents the design of an adaptive competitive self-organizing associative memory (ACSAM) system for use in classification and recognition of pattern information. Volterra and Lotka's models of interacting species in biology motivated the ACSAM model; a model based on a system of nonlinear ordinary differential equations (ODEs). Self-organizing behavior is modeled for unsupervised neural networks employing the concept of interacting/competing species in biology. In this model, self-organizing properties can be implicitly coded within the systems trajectory structure using only ODEs. Among the features of this continuous-time system are: 1) the dynamic behavior is well-understood and characterized; 2) the desired fixed points are the only asymptotically stable states of the system; 3) the trajectories of ACSAM derived from the weight activities of the gradient system have no periodic or homoclinic orbits; and 4) the heteroclinic orbits that exist between equilibrium states are structurally unstable and can be removed by small perturbations.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TSMCA.2002.804789</doi><tpages>11</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1083-4427 |
| ispartof | IEEE transactions on systems, man and cybernetics. Part A, Systems and humans, 2002-07, Vol.32 (4), p.461-471 |
| issn | 1083-4427 2168-2216 1558-2426 2168-2232 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_28913774 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Associative memory Asymptotic properties Biological system modeling Biology Clustering algorithms Computational biology Differential equations Dynamical systems Dynamics Neural networks Neurons Nonlinear dynamics Orbits Ordinary differential equations Pattern recognition Prototypes Studies Trajectories |
| title | Adaptive competitive self-organizing associative memory |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T02%3A36%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Adaptive%20competitive%20self-organizing%20associative%20memory&rft.jtitle=IEEE%20transactions%20on%20systems,%20man%20and%20cybernetics.%20Part%20A,%20Systems%20and%20humans&rft.au=Athinarayanan,%20R.&rft.date=2002-07-01&rft.volume=32&rft.issue=4&rft.spage=461&rft.epage=471&rft.pages=461-471&rft.issn=1083-4427&rft.eissn=1558-2426&rft.coden=ITSHFX&rft_id=info:doi/10.1109/TSMCA.2002.804789&rft_dat=%3Cproquest_RIE%3E28202520%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=884495255&rft_id=info:pmid/&rft_ieee_id=1158963&rfr_iscdi=true |