EKENS: a learning on nonlinear blindly mixed signals
We present experimental results of the blind separation of independent sources from their nonlinear mixtures. The proposed EKENS (equivariant kernel nonlinear separation) algorithm is a generalization of a natural gradient algorithm and the Gram-Charlier series, which is extended in two ways: (1) to...
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 | iv/84 Vol. 4 |
|---|---|
| container_issue | |
| container_start_page | iv/81 |
| container_title | |
| container_volume | 4 |
| creator | Leong, W.Y. Homer, J. |
| description | We present experimental results of the blind separation of independent sources from their nonlinear mixtures. The proposed EKENS (equivariant kernel nonlinear separation) algorithm is a generalization of a natural gradient algorithm and the Gram-Charlier series, which is extended in two ways: (1) to deal with nonlinear mapping; (2) to be able to adapt to the actual statistical distributions of the sources by estimating the kernel density distribution at the output signals. The observations are modelled based on nonlinear generative multilayer perceptron analysis. The theory of the EKENS learning algorithm is discussed. Simulations show that the EKENS algorithm is able to find the underlying sources from the observation, even though the data generating mapping is nonlinear and unknown. |
| doi_str_mv | 10.1109/ICASSP.2005.1415950 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1415950</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1415950</ieee_id><sourcerecordid>1415950</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-70e5021e57aa8c3342c1c3eded54e22d9665b9ff8aa0def5fe0319665ca6b65f3</originalsourceid><addsrcrecordid>eNotj01Lw0AYhBc_wFDzC3rZP5D47nfWm5RoxaJCevBWNtl3y0q6lcSD_feu2GHggTkMM4QsGdSMgb17Xj103XvNAVTNJFNWwQUpuDC2YhY-LklpTQPZommMZFekYIpDpZm0N6Sc50_I0twYLQsi25f2tbunjo7ophTTnh4TTcc0xpQD2mf68UQP8Qc9neM-uXG-JdchA8szF2T72G5X62rz9pTXbapo4bsygAo4Q2WcawYhJB_YINCjVxI591Zr1dsQGufAY1ABQbC_cHC61yqIBVn-10ZE3H1N8eCm0-58WfwChm1H0A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>EKENS: a learning on nonlinear blindly mixed signals</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Leong, W.Y. ; Homer, J.</creator><creatorcontrib>Leong, W.Y. ; Homer, J.</creatorcontrib><description>We present experimental results of the blind separation of independent sources from their nonlinear mixtures. The proposed EKENS (equivariant kernel nonlinear separation) algorithm is a generalization of a natural gradient algorithm and the Gram-Charlier series, which is extended in two ways: (1) to deal with nonlinear mapping; (2) to be able to adapt to the actual statistical distributions of the sources by estimating the kernel density distribution at the output signals. The observations are modelled based on nonlinear generative multilayer perceptron analysis. The theory of the EKENS learning algorithm is discussed. Simulations show that the EKENS algorithm is able to find the underlying sources from the observation, even though the data generating mapping is nonlinear and unknown.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9780780388741</identifier><identifier>ISBN: 0780388747</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2005.1415950</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cancer ; Distribution functions ; Gaussian distribution ; Information technology ; Kernel ; Polynomials ; Probability density function ; Probability distribution ; Random variables ; Vectors</subject><ispartof>Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005, 2005, Vol.4, p.iv/81-iv/84 Vol. 4</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/1415950$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1415950$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Leong, W.Y.</creatorcontrib><creatorcontrib>Homer, J.</creatorcontrib><title>EKENS: a learning on nonlinear blindly mixed signals</title><title>Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005</title><addtitle>ICASSP</addtitle><description>We present experimental results of the blind separation of independent sources from their nonlinear mixtures. The proposed EKENS (equivariant kernel nonlinear separation) algorithm is a generalization of a natural gradient algorithm and the Gram-Charlier series, which is extended in two ways: (1) to deal with nonlinear mapping; (2) to be able to adapt to the actual statistical distributions of the sources by estimating the kernel density distribution at the output signals. The observations are modelled based on nonlinear generative multilayer perceptron analysis. The theory of the EKENS learning algorithm is discussed. Simulations show that the EKENS algorithm is able to find the underlying sources from the observation, even though the data generating mapping is nonlinear and unknown.</description><subject>Cancer</subject><subject>Distribution functions</subject><subject>Gaussian distribution</subject><subject>Information technology</subject><subject>Kernel</subject><subject>Polynomials</subject><subject>Probability density function</subject><subject>Probability distribution</subject><subject>Random variables</subject><subject>Vectors</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9780780388741</isbn><isbn>0780388747</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj01Lw0AYhBc_wFDzC3rZP5D47nfWm5RoxaJCevBWNtl3y0q6lcSD_feu2GHggTkMM4QsGdSMgb17Xj103XvNAVTNJFNWwQUpuDC2YhY-LklpTQPZommMZFekYIpDpZm0N6Sc50_I0twYLQsi25f2tbunjo7ophTTnh4TTcc0xpQD2mf68UQP8Qc9neM-uXG-JdchA8szF2T72G5X62rz9pTXbapo4bsygAo4Q2WcawYhJB_YINCjVxI591Zr1dsQGufAY1ABQbC_cHC61yqIBVn-10ZE3H1N8eCm0-58WfwChm1H0A</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Leong, W.Y.</creator><creator>Homer, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2005</creationdate><title>EKENS: a learning on nonlinear blindly mixed signals</title><author>Leong, W.Y. ; Homer, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-70e5021e57aa8c3342c1c3eded54e22d9665b9ff8aa0def5fe0319665ca6b65f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Cancer</topic><topic>Distribution functions</topic><topic>Gaussian distribution</topic><topic>Information technology</topic><topic>Kernel</topic><topic>Polynomials</topic><topic>Probability density function</topic><topic>Probability distribution</topic><topic>Random variables</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Leong, W.Y.</creatorcontrib><creatorcontrib>Homer, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Leong, W.Y.</au><au>Homer, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>EKENS: a learning on nonlinear blindly mixed signals</atitle><btitle>Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005</btitle><stitle>ICASSP</stitle><date>2005</date><risdate>2005</risdate><volume>4</volume><spage>iv/81</spage><epage>iv/84 Vol. 4</epage><pages>iv/81-iv/84 Vol. 4</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9780780388741</isbn><isbn>0780388747</isbn><abstract>We present experimental results of the blind separation of independent sources from their nonlinear mixtures. The proposed EKENS (equivariant kernel nonlinear separation) algorithm is a generalization of a natural gradient algorithm and the Gram-Charlier series, which is extended in two ways: (1) to deal with nonlinear mapping; (2) to be able to adapt to the actual statistical distributions of the sources by estimating the kernel density distribution at the output signals. The observations are modelled based on nonlinear generative multilayer perceptron analysis. The theory of the EKENS learning algorithm is discussed. Simulations show that the EKENS algorithm is able to find the underlying sources from the observation, even though the data generating mapping is nonlinear and unknown.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2005.1415950</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005, 2005, Vol.4, p.iv/81-iv/84 Vol. 4 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_1415950 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Cancer Distribution functions Gaussian distribution Information technology Kernel Polynomials Probability density function Probability distribution Random variables Vectors |
| title | EKENS: a learning on nonlinear blindly mixed signals |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-30T17%3A27%3A55IST&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=EKENS:%20a%20learning%20on%20nonlinear%20blindly%20mixed%20signals&rft.btitle=Proceedings.%20(ICASSP%20'05).%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing,%202005&rft.au=Leong,%20W.Y.&rft.date=2005&rft.volume=4&rft.spage=iv/81&rft.epage=iv/84%20Vol.%204&rft.pages=iv/81-iv/84%20Vol.%204&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9780780388741&rft.isbn_list=0780388747&rft_id=info:doi/10.1109/ICASSP.2005.1415950&rft_dat=%3Cieee_6IE%3E1415950%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1415950&rfr_iscdi=true |