Loading…
Local Variance Driven Self-Organization for Unsupervised Clustering
We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approa...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 424 |
| container_issue | |
| container_start_page | 421 |
| container_title | |
| container_volume | 3 |
| creator | Kyan, M. Ling Guan |
| description | We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approach uses a vigilance based, global parsing strategy as a guide for the hierarchical partitioning of an underlying data distribution into a set of dominant prototypes: each consisting of a dual memory element for the online estimation of both position and maximal local variance. A co-operative scheme exploits the interplay between global vigilance and maximal local variance such that an informed choice may be made regarding insertion sites for new nodes into the map. The network is related to self-organizing tree maps (SOTM), growing neural gas (GNG) and their variants. A framework is presented and performance demonstrated against GNG |
| doi_str_mv | 10.1109/ICPR.2006.772 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1699554</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1699554</ieee_id><sourcerecordid>1699554</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-1788239d519c0370d416420cbadaea0f34107f71613465cdc138918c1ac1f34d3</originalsourceid><addsrcrecordid>eNotj81KAzEYRYM_YK1dunIzL5Dx-_I7WcpotTBQUeu2xCRTIuNMSaYFfXoH9G7u4sDlXEKuEUpEMLer-vmlZACq1JqdkBmrOFIttDwll6CVkUwyhDMyQ5BIhZJ4QRY5f8IUIaVgZkbqZnC2K95tirZ3obhP8Rj64jV0LV2nne3jjx3j0BftkIpNnw_7kI4xB1_U3SGPIcV-d0XOW9vlsPjvOdksH97qJ9qsH1f1XUMjajlS1FXFuPESjQOuwQtUgoH7sN4GCy0XCLrVqJBPrs475JXByqF1OEHP5-TmbzeGELb7FL9s-t6iMmY6w38By7BK-A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Local Variance Driven Self-Organization for Unsupervised Clustering</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Kyan, M. ; Ling Guan</creator><creatorcontrib>Kyan, M. ; Ling Guan</creatorcontrib><description>We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approach uses a vigilance based, global parsing strategy as a guide for the hierarchical partitioning of an underlying data distribution into a set of dominant prototypes: each consisting of a dual memory element for the online estimation of both position and maximal local variance. A co-operative scheme exploits the interplay between global vigilance and maximal local variance such that an informed choice may be made regarding insertion sites for new nodes into the map. The network is related to self-organizing tree maps (SOTM), growing neural gas (GNG) and their variants. A framework is presented and performance demonstrated against GNG</description><identifier>ISSN: 1051-4651</identifier><identifier>ISBN: 0769525210</identifier><identifier>ISBN: 9780769525211</identifier><identifier>EISSN: 2831-7475</identifier><identifier>DOI: 10.1109/ICPR.2006.772</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bioinformatics ; Clustering algorithms ; Data mining ; Genetics ; Hebbian theory ; Mining industry ; Partitioning algorithms ; Pattern recognition ; Prototypes ; Unsupervised learning</subject><ispartof>18th International Conference on Pattern Recognition (ICPR'06), 2006, Vol.3, p.421-424</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/1699554$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,4035,4036,27904,54534,54899,54911</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1699554$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Kyan, M.</creatorcontrib><creatorcontrib>Ling Guan</creatorcontrib><title>Local Variance Driven Self-Organization for Unsupervised Clustering</title><title>18th International Conference on Pattern Recognition (ICPR'06)</title><addtitle>ICPR</addtitle><description>We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approach uses a vigilance based, global parsing strategy as a guide for the hierarchical partitioning of an underlying data distribution into a set of dominant prototypes: each consisting of a dual memory element for the online estimation of both position and maximal local variance. A co-operative scheme exploits the interplay between global vigilance and maximal local variance such that an informed choice may be made regarding insertion sites for new nodes into the map. The network is related to self-organizing tree maps (SOTM), growing neural gas (GNG) and their variants. A framework is presented and performance demonstrated against GNG</description><subject>Bioinformatics</subject><subject>Clustering algorithms</subject><subject>Data mining</subject><subject>Genetics</subject><subject>Hebbian theory</subject><subject>Mining industry</subject><subject>Partitioning algorithms</subject><subject>Pattern recognition</subject><subject>Prototypes</subject><subject>Unsupervised learning</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>0769525210</isbn><isbn>9780769525211</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81KAzEYRYM_YK1dunIzL5Dx-_I7WcpotTBQUeu2xCRTIuNMSaYFfXoH9G7u4sDlXEKuEUpEMLer-vmlZACq1JqdkBmrOFIttDwll6CVkUwyhDMyQ5BIhZJ4QRY5f8IUIaVgZkbqZnC2K95tirZ3obhP8Rj64jV0LV2nne3jjx3j0BftkIpNnw_7kI4xB1_U3SGPIcV-d0XOW9vlsPjvOdksH97qJ9qsH1f1XUMjajlS1FXFuPESjQOuwQtUgoH7sN4GCy0XCLrVqJBPrs475JXByqF1OEHP5-TmbzeGELb7FL9s-t6iMmY6w38By7BK-A</recordid><startdate>2006</startdate><enddate>2006</enddate><creator>Kyan, M.</creator><creator>Ling Guan</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2006</creationdate><title>Local Variance Driven Self-Organization for Unsupervised Clustering</title><author>Kyan, M. ; Ling Guan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-1788239d519c0370d416420cbadaea0f34107f71613465cdc138918c1ac1f34d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Bioinformatics</topic><topic>Clustering algorithms</topic><topic>Data mining</topic><topic>Genetics</topic><topic>Hebbian theory</topic><topic>Mining industry</topic><topic>Partitioning algorithms</topic><topic>Pattern recognition</topic><topic>Prototypes</topic><topic>Unsupervised learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Kyan, M.</creatorcontrib><creatorcontrib>Ling Guan</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>Kyan, M.</au><au>Ling Guan</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Local Variance Driven Self-Organization for Unsupervised Clustering</atitle><btitle>18th International Conference on Pattern Recognition (ICPR'06)</btitle><stitle>ICPR</stitle><date>2006</date><risdate>2006</risdate><volume>3</volume><spage>421</spage><epage>424</epage><pages>421-424</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><isbn>0769525210</isbn><isbn>9780769525211</isbn><abstract>We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approach uses a vigilance based, global parsing strategy as a guide for the hierarchical partitioning of an underlying data distribution into a set of dominant prototypes: each consisting of a dual memory element for the online estimation of both position and maximal local variance. A co-operative scheme exploits the interplay between global vigilance and maximal local variance such that an informed choice may be made regarding insertion sites for new nodes into the map. The network is related to self-organizing tree maps (SOTM), growing neural gas (GNG) and their variants. A framework is presented and performance demonstrated against GNG</abstract><pub>IEEE</pub><doi>10.1109/ICPR.2006.772</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-4651 |
| ispartof | 18th International Conference on Pattern Recognition (ICPR'06), 2006, Vol.3, p.421-424 |
| issn | 1051-4651 2831-7475 |
| language | eng |
| recordid | cdi_ieee_primary_1699554 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Bioinformatics Clustering algorithms Data mining Genetics Hebbian theory Mining industry Partitioning algorithms Pattern recognition Prototypes Unsupervised learning |
| title | Local Variance Driven Self-Organization for Unsupervised Clustering |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T07%3A37%3A34IST&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=Local%20Variance%20Driven%20Self-Organization%20for%20Unsupervised%20Clustering&rft.btitle=18th%20International%20Conference%20on%20Pattern%20Recognition%20(ICPR'06)&rft.au=Kyan,%20M.&rft.date=2006&rft.volume=3&rft.spage=421&rft.epage=424&rft.pages=421-424&rft.issn=1051-4651&rft.eissn=2831-7475&rft.isbn=0769525210&rft.isbn_list=9780769525211&rft_id=info:doi/10.1109/ICPR.2006.772&rft_dat=%3Cieee_6IE%3E1699554%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-1788239d519c0370d416420cbadaea0f34107f71613465cdc138918c1ac1f34d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1699554&rfr_iscdi=true |