A dynamical adaptive resonance architecture
A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg (1987). It is shown how these differential equations allow the ART1 model to be...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on neural networks 1994-11, Vol.5 (6), p.873-889 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 889 |
|---|---|
| container_issue | 6 |
| container_start_page | 873 |
| container_title | IEEE transactions on neural networks |
| container_volume | 5 |
| creator | Heileman, G.L. Georgiopoulos, M. Abdallah, C. |
| description | A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg (1987). It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.< > |
| doi_str_mv | 10.1109/72.329684 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_329684</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>329684</ieee_id><sourcerecordid>28289432</sourcerecordid><originalsourceid>FETCH-LOGICAL-c427t-2a865e97f9854b7ef0c95884ad0673f9f6217af1471b21e9ba2b324a8a70f5f3</originalsourceid><addsrcrecordid>eNqF0E1LwzAYwPEgitPpwasH6UEUkc68NslxDN9g4GX3kqZPsNKXmbTCvr2RFnfTXBLIj-eBP0IXBC8IwfpB0gWjOlP8AJ0QzUmKsWaH8Y25SDWlcoZOQ_jAmHCBs2M0I4pmUmX0BN0vk3LXmqaypk5MabZ99QWJh9C1prWQGG_fqx5sP3g4Q0fO1AHOp3uONk-Pm9VLun57fl0t16nlVPYpNSoToKXTSvBCgsNWC6W4KXEmmdMuo0QaR7gkBSWgC0MLRrlRRmInHJuj23Hs1nefA4Q-b6pgoa5NC90QcsniGkyYivLmT0kVVZoz-j_MmBBcyAjvRmh9F4IHl2991Ri_ywnOf1rnkuZj62ivpqFD0UC5l1PcCK4nYELM63wsWoVfx-KJLrLLkVUAsP8dl3wDIFuLrw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>26355457</pqid></control><display><type>article</type><title>A dynamical adaptive resonance architecture</title><source>IEEE Electronic Library (IEL)</source><creator>Heileman, G.L. ; Georgiopoulos, M. ; Abdallah, C.</creator><creatorcontrib>Heileman, G.L. ; Georgiopoulos, M. ; Abdallah, C.</creatorcontrib><description>A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg (1987). It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.< ></description><identifier>ISSN: 1045-9227</identifier><identifier>EISSN: 1941-0093</identifier><identifier>DOI: 10.1109/72.329684</identifier><identifier>PMID: 18267862</identifier><identifier>CODEN: ITNNEP</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Applied sciences ; Artificial intelligence ; Chaos ; Circuits ; Computer architecture ; Computer science; control theory; systems ; Connectionism. Neural networks ; Differential equations ; Exact sciences and technology ; Mathematical model ; Neural networks ; Nonlinear dynamical systems ; Nonlinear equations ; Resonance</subject><ispartof>IEEE transactions on neural networks, 1994-11, Vol.5 (6), p.873-889</ispartof><rights>1995 INIST-CNRS</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c427t-2a865e97f9854b7ef0c95884ad0673f9f6217af1471b21e9ba2b324a8a70f5f3</citedby><cites>FETCH-LOGICAL-c427t-2a865e97f9854b7ef0c95884ad0673f9f6217af1471b21e9ba2b324a8a70f5f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/329684$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27929,27930,54763</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/329684$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=3333786$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18267862$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Heileman, G.L.</creatorcontrib><creatorcontrib>Georgiopoulos, M.</creatorcontrib><creatorcontrib>Abdallah, C.</creatorcontrib><title>A dynamical adaptive resonance architecture</title><title>IEEE transactions on neural networks</title><addtitle>TNN</addtitle><addtitle>IEEE Trans Neural Netw</addtitle><description>A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg (1987). It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.< ></description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Chaos</subject><subject>Circuits</subject><subject>Computer architecture</subject><subject>Computer science; control theory; systems</subject><subject>Connectionism. Neural networks</subject><subject>Differential equations</subject><subject>Exact sciences and technology</subject><subject>Mathematical model</subject><subject>Neural networks</subject><subject>Nonlinear dynamical systems</subject><subject>Nonlinear equations</subject><subject>Resonance</subject><issn>1045-9227</issn><issn>1941-0093</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1994</creationdate><recordtype>article</recordtype><recordid>eNqF0E1LwzAYwPEgitPpwasH6UEUkc68NslxDN9g4GX3kqZPsNKXmbTCvr2RFnfTXBLIj-eBP0IXBC8IwfpB0gWjOlP8AJ0QzUmKsWaH8Y25SDWlcoZOQ_jAmHCBs2M0I4pmUmX0BN0vk3LXmqaypk5MabZ99QWJh9C1prWQGG_fqx5sP3g4Q0fO1AHOp3uONk-Pm9VLun57fl0t16nlVPYpNSoToKXTSvBCgsNWC6W4KXEmmdMuo0QaR7gkBSWgC0MLRrlRRmInHJuj23Hs1nefA4Q-b6pgoa5NC90QcsniGkyYivLmT0kVVZoz-j_MmBBcyAjvRmh9F4IHl2991Ri_ywnOf1rnkuZj62ivpqFD0UC5l1PcCK4nYELM63wsWoVfx-KJLrLLkVUAsP8dl3wDIFuLrw</recordid><startdate>19941101</startdate><enddate>19941101</enddate><creator>Heileman, G.L.</creator><creator>Georgiopoulos, M.</creator><creator>Abdallah, C.</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>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope></search><sort><creationdate>19941101</creationdate><title>A dynamical adaptive resonance architecture</title><author>Heileman, G.L. ; Georgiopoulos, M. ; Abdallah, C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c427t-2a865e97f9854b7ef0c95884ad0673f9f6217af1471b21e9ba2b324a8a70f5f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1994</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Chaos</topic><topic>Circuits</topic><topic>Computer architecture</topic><topic>Computer science; control theory; systems</topic><topic>Connectionism. Neural networks</topic><topic>Differential equations</topic><topic>Exact sciences and technology</topic><topic>Mathematical model</topic><topic>Neural networks</topic><topic>Nonlinear dynamical systems</topic><topic>Nonlinear equations</topic><topic>Resonance</topic><toplevel>online_resources</toplevel><creatorcontrib>Heileman, G.L.</creatorcontrib><creatorcontrib>Georgiopoulos, M.</creatorcontrib><creatorcontrib>Abdallah, C.</creatorcontrib><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications 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_linktorsrc</fulltext></delivery><addata><au>Heileman, G.L.</au><au>Georgiopoulos, M.</au><au>Abdallah, C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A dynamical adaptive resonance architecture</atitle><jtitle>IEEE transactions on neural networks</jtitle><stitle>TNN</stitle><addtitle>IEEE Trans Neural Netw</addtitle><date>1994-11-01</date><risdate>1994</risdate><volume>5</volume><issue>6</issue><spage>873</spage><epage>889</epage><pages>873-889</pages><issn>1045-9227</issn><eissn>1941-0093</eissn><coden>ITNNEP</coden><abstract>A set of nonlinear differential equations that describe the dynamics of the ART1 model are presented, along with the motivation for their use. These equations are extensions of those developed by Carpenter and Grossberg (1987). It is shown how these differential equations allow the ART1 model to be realized as a collective nonlinear dynamical system. Specifically, we present an ART1-based neural network model whose description requires no external control features. That is, the dynamics of the model are completely determined by the set of coupled differential equations that comprise the model. It is shown analytically how the parameters of this model can be selected so as to guarantee a behavior equivalent to that of ART1 in both fast and slow learning scenarios. Simulations are performed in which the trajectories of node and weight activities are determined using numerical approximation techniques.< ></abstract><cop>New York, NY</cop><pub>IEEE</pub><pmid>18267862</pmid><doi>10.1109/72.329684</doi><tpages>17</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1045-9227 |
| ispartof | IEEE transactions on neural networks, 1994-11, Vol.5 (6), p.873-889 |
| issn | 1045-9227 1941-0093 |
| language | eng |
| recordid | cdi_ieee_primary_329684 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Artificial intelligence Chaos Circuits Computer architecture Computer science control theory systems Connectionism. Neural networks Differential equations Exact sciences and technology Mathematical model Neural networks Nonlinear dynamical systems Nonlinear equations Resonance |
| title | A dynamical adaptive resonance architecture |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T10%3A41%3A16IST&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=A%20dynamical%20adaptive%20resonance%20architecture&rft.jtitle=IEEE%20transactions%20on%20neural%20networks&rft.au=Heileman,%20G.L.&rft.date=1994-11-01&rft.volume=5&rft.issue=6&rft.spage=873&rft.epage=889&rft.pages=873-889&rft.issn=1045-9227&rft.eissn=1941-0093&rft.coden=ITNNEP&rft_id=info:doi/10.1109/72.329684&rft_dat=%3Cproquest_RIE%3E28289432%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=26355457&rft_id=info:pmid/18267862&rft_ieee_id=329684&rfr_iscdi=true |