Unsupervised Segmentation With Dynamical Units
In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that c...
Gespeichert in:
| Veröffentlicht in: | IEEE transaction on neural networks and learning systems 2008-01, Vol.19 (1), p.168-182 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 182 |
|---|---|
| container_issue | 1 |
| container_start_page | 168 |
| container_title | IEEE transaction on neural networks and learning systems |
| container_volume | 19 |
| creator | Ravishankar Rao, A. Cecchi, G.A. Peck, C.C. Kozloski, J.R. |
| description | In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that can synchronize their dynamics, so that separation is determined by the amplitude of units in an output layer, and segmentation by phase similarity between input and output layer units. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. Moreover, efficient segmentation can be achieved even when there is considerable superposition of the inputs. The network dynamics are derived from an objective function that rewards sparse coding in the generalized amplitude-phase variables. We argue that this objective function can provide a possible formal interpretation of the binding problem and that the implementation of the network architecture and dynamics is biologically plausible. |
| doi_str_mv | 10.1109/TNN.2007.905852 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_18269948</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4359215</ieee_id><sourcerecordid>70297165</sourcerecordid><originalsourceid>FETCH-LOGICAL-c404t-48d39962cb63fba58fda0860edc2a09b341decc18e55dfb4a4d8bdcf152e9b63</originalsourceid><addsrcrecordid>eNp90c1LwzAYBvAgih_TswdBhqCeOt-kSZscZX7C0IMTjyFN3mpkbWfTCvvvzdiY4MFcEsjvfSBPCDmmMKIU1NX06WnEAPKRAiEF2yL7VHGaAKh0O56Bi0Qxlu-RgxA-ASgXkO2SPSpZphSX-2T0Wod-ju23D-iGL_heYd2Zzjf18M13H8ObRW0qb81s-Fr7LhySndLMAh6t9wGZ3t1Oxw_J5Pn-cXw9SSwH3iVculSpjNkiS8vCCFk6AzIDdJYZUEXKqUNrqUQhXFlww50snC2pYKjizIBcrmLnbfPVY-h05YPF2czU2PRBy1yAlJyJKC_-lTkwldNsCc_-wM-mb-v4CK0oS_O4ZERXK2TbJoQWSz1vfWXahaagl4XrWLheFq5XhceJ03VsX1Tofv264QjO18CEWGPZmtr6sHExC0T8suhOVs4j4uaap0IxKtIfwA-QJA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>912377778</pqid></control><display><type>article</type><title>Unsupervised Segmentation With Dynamical Units</title><source>IEEE Electronic Library (IEL)</source><creator>Ravishankar Rao, A. ; Cecchi, G.A. ; Peck, C.C. ; Kozloski, J.R.</creator><creatorcontrib>Ravishankar Rao, A. ; Cecchi, G.A. ; Peck, C.C. ; Kozloski, J.R.</creatorcontrib><description>In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that can synchronize their dynamics, so that separation is determined by the amplitude of units in an output layer, and segmentation by phase similarity between input and output layer units. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. Moreover, efficient segmentation can be achieved even when there is considerable superposition of the inputs. The network dynamics are derived from an objective function that rewards sparse coding in the generalized amplitude-phase variables. We argue that this objective function can provide a possible formal interpretation of the binding problem and that the implementation of the network architecture and dynamics is biologically plausible.</description><identifier>ISSN: 1045-9227</identifier><identifier>ISSN: 2162-237X</identifier><identifier>EISSN: 1941-0093</identifier><identifier>EISSN: 2162-2388</identifier><identifier>DOI: 10.1109/TNN.2007.905852</identifier><identifier>PMID: 18269948</identifier><identifier>CODEN: ITNNEP</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Applied sciences ; Architecture ; Artificial Intelligence ; Binding problem ; Biological information theory ; Biology computing ; Classification ; Computer architecture ; Computer science; control theory; systems ; Computer systems and distributed systems. User interface ; Connectionism. Neural networks ; Deconvolution ; Dynamics ; Exact sciences and technology ; Humans ; Layout ; Learning - physiology ; Nerve Net ; Networks ; Neural networks ; Neural Networks (Computer) ; Nonlinear Dynamics ; oscillations ; Pattern Recognition, Automated ; phase correlation ; Quantum computing ; Segmentation ; Segments ; separation of mixtures ; Similarity ; Software ; Studies ; synchronization ; Visual system</subject><ispartof>IEEE transaction on neural networks and learning systems, 2008-01, Vol.19 (1), p.168-182</ispartof><rights>2008 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c404t-48d39962cb63fba58fda0860edc2a09b341decc18e55dfb4a4d8bdcf152e9b63</citedby><cites>FETCH-LOGICAL-c404t-48d39962cb63fba58fda0860edc2a09b341decc18e55dfb4a4d8bdcf152e9b63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4359215$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4024,27923,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4359215$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20005941$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18269948$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ravishankar Rao, A.</creatorcontrib><creatorcontrib>Cecchi, G.A.</creatorcontrib><creatorcontrib>Peck, C.C.</creatorcontrib><creatorcontrib>Kozloski, J.R.</creatorcontrib><title>Unsupervised Segmentation With Dynamical Units</title><title>IEEE transaction on neural networks and learning systems</title><addtitle>TNN</addtitle><addtitle>IEEE Trans Neural Netw</addtitle><description>In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that can synchronize their dynamics, so that separation is determined by the amplitude of units in an output layer, and segmentation by phase similarity between input and output layer units. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. Moreover, efficient segmentation can be achieved even when there is considerable superposition of the inputs. The network dynamics are derived from an objective function that rewards sparse coding in the generalized amplitude-phase variables. We argue that this objective function can provide a possible formal interpretation of the binding problem and that the implementation of the network architecture and dynamics is biologically plausible.</description><subject>Applied sciences</subject><subject>Architecture</subject><subject>Artificial Intelligence</subject><subject>Binding problem</subject><subject>Biological information theory</subject><subject>Biology computing</subject><subject>Classification</subject><subject>Computer architecture</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems and distributed systems. User interface</subject><subject>Connectionism. Neural networks</subject><subject>Deconvolution</subject><subject>Dynamics</subject><subject>Exact sciences and technology</subject><subject>Humans</subject><subject>Layout</subject><subject>Learning - physiology</subject><subject>Nerve Net</subject><subject>Networks</subject><subject>Neural networks</subject><subject>Neural Networks (Computer)</subject><subject>Nonlinear Dynamics</subject><subject>oscillations</subject><subject>Pattern Recognition, Automated</subject><subject>phase correlation</subject><subject>Quantum computing</subject><subject>Segmentation</subject><subject>Segments</subject><subject>separation of mixtures</subject><subject>Similarity</subject><subject>Software</subject><subject>Studies</subject><subject>synchronization</subject><subject>Visual system</subject><issn>1045-9227</issn><issn>2162-237X</issn><issn>1941-0093</issn><issn>2162-2388</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNp90c1LwzAYBvAgih_TswdBhqCeOt-kSZscZX7C0IMTjyFN3mpkbWfTCvvvzdiY4MFcEsjvfSBPCDmmMKIU1NX06WnEAPKRAiEF2yL7VHGaAKh0O56Bi0Qxlu-RgxA-ASgXkO2SPSpZphSX-2T0Wod-ju23D-iGL_heYd2Zzjf18M13H8ObRW0qb81s-Fr7LhySndLMAh6t9wGZ3t1Oxw_J5Pn-cXw9SSwH3iVculSpjNkiS8vCCFk6AzIDdJYZUEXKqUNrqUQhXFlww50snC2pYKjizIBcrmLnbfPVY-h05YPF2czU2PRBy1yAlJyJKC_-lTkwldNsCc_-wM-mb-v4CK0oS_O4ZERXK2TbJoQWSz1vfWXahaagl4XrWLheFq5XhceJ03VsX1Tofv264QjO18CEWGPZmtr6sHExC0T8suhOVs4j4uaap0IxKtIfwA-QJA</recordid><startdate>200801</startdate><enddate>200801</enddate><creator>Ravishankar Rao, A.</creator><creator>Cecchi, G.A.</creator><creator>Peck, C.C.</creator><creator>Kozloski, J.R.</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QO</scope><scope>7QP</scope><scope>7QQ</scope><scope>7QR</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7TK</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>200801</creationdate><title>Unsupervised Segmentation With Dynamical Units</title><author>Ravishankar Rao, A. ; Cecchi, G.A. ; Peck, C.C. ; Kozloski, J.R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c404t-48d39962cb63fba58fda0860edc2a09b341decc18e55dfb4a4d8bdcf152e9b63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Applied sciences</topic><topic>Architecture</topic><topic>Artificial Intelligence</topic><topic>Binding problem</topic><topic>Biological information theory</topic><topic>Biology computing</topic><topic>Classification</topic><topic>Computer architecture</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems and distributed systems. User interface</topic><topic>Connectionism. Neural networks</topic><topic>Deconvolution</topic><topic>Dynamics</topic><topic>Exact sciences and technology</topic><topic>Humans</topic><topic>Layout</topic><topic>Learning - physiology</topic><topic>Nerve Net</topic><topic>Networks</topic><topic>Neural networks</topic><topic>Neural Networks (Computer)</topic><topic>Nonlinear Dynamics</topic><topic>oscillations</topic><topic>Pattern Recognition, Automated</topic><topic>phase correlation</topic><topic>Quantum computing</topic><topic>Segmentation</topic><topic>Segments</topic><topic>separation of mixtures</topic><topic>Similarity</topic><topic>Software</topic><topic>Studies</topic><topic>synchronization</topic><topic>Visual system</topic><toplevel>online_resources</toplevel><creatorcontrib>Ravishankar Rao, A.</creatorcontrib><creatorcontrib>Cecchi, G.A.</creatorcontrib><creatorcontrib>Peck, C.C.</creatorcontrib><creatorcontrib>Kozloski, J.R.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</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>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transaction on neural networks and learning systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ravishankar Rao, A.</au><au>Cecchi, G.A.</au><au>Peck, C.C.</au><au>Kozloski, J.R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unsupervised Segmentation With Dynamical Units</atitle><jtitle>IEEE transaction on neural networks and learning systems</jtitle><stitle>TNN</stitle><addtitle>IEEE Trans Neural Netw</addtitle><date>2008-01</date><risdate>2008</risdate><volume>19</volume><issue>1</issue><spage>168</spage><epage>182</epage><pages>168-182</pages><issn>1045-9227</issn><issn>2162-237X</issn><eissn>1941-0093</eissn><eissn>2162-2388</eissn><coden>ITNNEP</coden><abstract>In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that can synchronize their dynamics, so that separation is determined by the amplitude of units in an output layer, and segmentation by phase similarity between input and output layer units. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. Moreover, efficient segmentation can be achieved even when there is considerable superposition of the inputs. The network dynamics are derived from an objective function that rewards sparse coding in the generalized amplitude-phase variables. We argue that this objective function can provide a possible formal interpretation of the binding problem and that the implementation of the network architecture and dynamics is biologically plausible.</abstract><cop>New York, NY</cop><pub>IEEE</pub><pmid>18269948</pmid><doi>10.1109/TNN.2007.905852</doi><tpages>15</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1045-9227 |
| ispartof | IEEE transaction on neural networks and learning systems, 2008-01, Vol.19 (1), p.168-182 |
| issn | 1045-9227 2162-237X 1941-0093 2162-2388 |
| language | eng |
| recordid | cdi_pubmed_primary_18269948 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Architecture Artificial Intelligence Binding problem Biological information theory Biology computing Classification Computer architecture Computer science control theory systems Computer systems and distributed systems. User interface Connectionism. Neural networks Deconvolution Dynamics Exact sciences and technology Humans Layout Learning - physiology Nerve Net Networks Neural networks Neural Networks (Computer) Nonlinear Dynamics oscillations Pattern Recognition, Automated phase correlation Quantum computing Segmentation Segments separation of mixtures Similarity Software Studies synchronization Visual system |
| title | Unsupervised Segmentation With Dynamical Units |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T11%3A46%3A20IST&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=Unsupervised%20Segmentation%20With%20Dynamical%20Units&rft.jtitle=IEEE%20transaction%20on%20neural%20networks%20and%20learning%20systems&rft.au=Ravishankar%20Rao,%20A.&rft.date=2008-01&rft.volume=19&rft.issue=1&rft.spage=168&rft.epage=182&rft.pages=168-182&rft.issn=1045-9227&rft.eissn=1941-0093&rft.coden=ITNNEP&rft_id=info:doi/10.1109/TNN.2007.905852&rft_dat=%3Cproquest_RIE%3E70297165%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=912377778&rft_id=info:pmid/18269948&rft_ieee_id=4359215&rfr_iscdi=true |