A Converged Recurrent Structure for CMACGBF and SCMACGBF
A new recurrent structure has been developed for both CMAC_GBF and S_CMAC_GBF in this paper. From the view of control, CMAC_GBF is capable of its excellent learning ability and superior of its control of complex nonlinear systems, but it is difficult for CMAC_GBF to solve problems of dynamic or time...
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 | 1881 |
|---|---|
| container_issue | |
| container_start_page | 1876 |
| container_title | |
| container_volume | |
| creator | Ching-Tsan Chiang Tung-Sheng Chiang |
| description | A new recurrent structure has been developed for both CMAC_GBF and S_CMAC_GBF in this paper. From the view of control, CMAC_GBF is capable of its excellent learning ability and superior of its control of complex nonlinear systems, but it is difficult for CMAC_GBF to solve problems of dynamic or time-relevant systems. This study develops recurrent structure for CMAC_GBF and S_CMAC_GBF with the method of employing the output of each hypercube to feedback to itself. This approach makes CMAC_GBF and S_CMAC_GBF to have the learning capability of temporal pattern sequences, and has more complex learning capability and is better than static feedforward networks. The design of recurrent structure and the driven of mathematic formulas and learning rules were accomplished in this paper. The proof of the learning convergence of the recurrent structure for CMAC_GBF and S CMAC_GBF is completed. The examples of temporal pattern sequences was demonstrated for the dynamic leaning capability of this recurrent structure. |
| doi_str_mv | 10.1109/ISIE.2007.4374893 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4374893</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4374893</ieee_id><sourcerecordid>4374893</sourcerecordid><originalsourceid>FETCH-ieee_primary_43748933</originalsourceid><addsrcrecordid>eNp9jrEOgkAQBdeoiah8gLG5HwD3uMODEgkqhY3YEwKLwSiYA0z8ey2wdZqXyWsGYMXR5hz9TZzEke0gKlsKJT1fjMD0lcelIyUq13XGMP-JxAkYDt8Ky-VCzcBs2xt-Eb7LEQ3wAhY29Yv0lQp2przXmuqOJZ3u867XxMpGs_AUhIfdnmV1wZJBljAts3tL5rALWO-jS3i0KiJKn7p6ZPqdDoHi__sBuR44Lw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A Converged Recurrent Structure for CMACGBF and SCMACGBF</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ching-Tsan Chiang ; Tung-Sheng Chiang</creator><creatorcontrib>Ching-Tsan Chiang ; Tung-Sheng Chiang</creatorcontrib><description>A new recurrent structure has been developed for both CMAC_GBF and S_CMAC_GBF in this paper. From the view of control, CMAC_GBF is capable of its excellent learning ability and superior of its control of complex nonlinear systems, but it is difficult for CMAC_GBF to solve problems of dynamic or time-relevant systems. This study develops recurrent structure for CMAC_GBF and S_CMAC_GBF with the method of employing the output of each hypercube to feedback to itself. This approach makes CMAC_GBF and S_CMAC_GBF to have the learning capability of temporal pattern sequences, and has more complex learning capability and is better than static feedforward networks. The design of recurrent structure and the driven of mathematic formulas and learning rules were accomplished in this paper. The proof of the learning convergence of the recurrent structure for CMAC_GBF and S CMAC_GBF is completed. The examples of temporal pattern sequences was demonstrated for the dynamic leaning capability of this recurrent structure.</description><identifier>ISSN: 2163-5137</identifier><identifier>ISBN: 1424407540</identifier><identifier>ISBN: 9781424407545</identifier><identifier>EISBN: 9781424407552</identifier><identifier>EISBN: 1424407559</identifier><identifier>DOI: 10.1109/ISIE.2007.4374893</identifier><language>eng</language><publisher>IEEE</publisher><subject>Associative memory ; Control systems ; Convergence ; Hypercubes ; Mathematics ; Nonlinear control systems ; Nonlinear systems ; Output feedback ; Quantization ; Testing</subject><ispartof>2007 IEEE International Symposium on Industrial Electronics, 2007, p.1876-1881</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/4374893$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4374893$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ching-Tsan Chiang</creatorcontrib><creatorcontrib>Tung-Sheng Chiang</creatorcontrib><title>A Converged Recurrent Structure for CMACGBF and SCMACGBF</title><title>2007 IEEE International Symposium on Industrial Electronics</title><addtitle>ISIE</addtitle><description>A new recurrent structure has been developed for both CMAC_GBF and S_CMAC_GBF in this paper. From the view of control, CMAC_GBF is capable of its excellent learning ability and superior of its control of complex nonlinear systems, but it is difficult for CMAC_GBF to solve problems of dynamic or time-relevant systems. This study develops recurrent structure for CMAC_GBF and S_CMAC_GBF with the method of employing the output of each hypercube to feedback to itself. This approach makes CMAC_GBF and S_CMAC_GBF to have the learning capability of temporal pattern sequences, and has more complex learning capability and is better than static feedforward networks. The design of recurrent structure and the driven of mathematic formulas and learning rules were accomplished in this paper. The proof of the learning convergence of the recurrent structure for CMAC_GBF and S CMAC_GBF is completed. The examples of temporal pattern sequences was demonstrated for the dynamic leaning capability of this recurrent structure.</description><subject>Associative memory</subject><subject>Control systems</subject><subject>Convergence</subject><subject>Hypercubes</subject><subject>Mathematics</subject><subject>Nonlinear control systems</subject><subject>Nonlinear systems</subject><subject>Output feedback</subject><subject>Quantization</subject><subject>Testing</subject><issn>2163-5137</issn><isbn>1424407540</isbn><isbn>9781424407545</isbn><isbn>9781424407552</isbn><isbn>1424407559</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNp9jrEOgkAQBdeoiah8gLG5HwD3uMODEgkqhY3YEwKLwSiYA0z8ey2wdZqXyWsGYMXR5hz9TZzEke0gKlsKJT1fjMD0lcelIyUq13XGMP-JxAkYDt8Ky-VCzcBs2xt-Eb7LEQ3wAhY29Yv0lQp2przXmuqOJZ3u867XxMpGs_AUhIfdnmV1wZJBljAts3tL5rALWO-jS3i0KiJKn7p6ZPqdDoHi__sBuR44Lw</recordid><startdate>200706</startdate><enddate>200706</enddate><creator>Ching-Tsan Chiang</creator><creator>Tung-Sheng Chiang</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200706</creationdate><title>A Converged Recurrent Structure for CMACGBF and SCMACGBF</title><author>Ching-Tsan Chiang ; Tung-Sheng Chiang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_43748933</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Associative memory</topic><topic>Control systems</topic><topic>Convergence</topic><topic>Hypercubes</topic><topic>Mathematics</topic><topic>Nonlinear control systems</topic><topic>Nonlinear systems</topic><topic>Output feedback</topic><topic>Quantization</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Ching-Tsan Chiang</creatorcontrib><creatorcontrib>Tung-Sheng Chiang</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>Ching-Tsan Chiang</au><au>Tung-Sheng Chiang</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A Converged Recurrent Structure for CMACGBF and SCMACGBF</atitle><btitle>2007 IEEE International Symposium on Industrial Electronics</btitle><stitle>ISIE</stitle><date>2007-06</date><risdate>2007</risdate><spage>1876</spage><epage>1881</epage><pages>1876-1881</pages><issn>2163-5137</issn><isbn>1424407540</isbn><isbn>9781424407545</isbn><eisbn>9781424407552</eisbn><eisbn>1424407559</eisbn><abstract>A new recurrent structure has been developed for both CMAC_GBF and S_CMAC_GBF in this paper. From the view of control, CMAC_GBF is capable of its excellent learning ability and superior of its control of complex nonlinear systems, but it is difficult for CMAC_GBF to solve problems of dynamic or time-relevant systems. This study develops recurrent structure for CMAC_GBF and S_CMAC_GBF with the method of employing the output of each hypercube to feedback to itself. This approach makes CMAC_GBF and S_CMAC_GBF to have the learning capability of temporal pattern sequences, and has more complex learning capability and is better than static feedforward networks. The design of recurrent structure and the driven of mathematic formulas and learning rules were accomplished in this paper. The proof of the learning convergence of the recurrent structure for CMAC_GBF and S CMAC_GBF is completed. The examples of temporal pattern sequences was demonstrated for the dynamic leaning capability of this recurrent structure.</abstract><pub>IEEE</pub><doi>10.1109/ISIE.2007.4374893</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2163-5137 |
| ispartof | 2007 IEEE International Symposium on Industrial Electronics, 2007, p.1876-1881 |
| issn | 2163-5137 |
| language | eng |
| recordid | cdi_ieee_primary_4374893 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Associative memory Control systems Convergence Hypercubes Mathematics Nonlinear control systems Nonlinear systems Output feedback Quantization Testing |
| title | A Converged Recurrent Structure for CMACGBF and SCMACGBF |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T10%3A59%3A33IST&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=A%20Converged%20Recurrent%20Structure%20for%20CMACGBF%20and%20SCMACGBF&rft.btitle=2007%20IEEE%20International%20Symposium%20on%20Industrial%20Electronics&rft.au=Ching-Tsan%20Chiang&rft.date=2007-06&rft.spage=1876&rft.epage=1881&rft.pages=1876-1881&rft.issn=2163-5137&rft.isbn=1424407540&rft.isbn_list=9781424407545&rft_id=info:doi/10.1109/ISIE.2007.4374893&rft_dat=%3Cieee_6IE%3E4374893%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424407552&rft.eisbn_list=1424407559&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4374893&rfr_iscdi=true |