A biologically motivated visual memory architecture for online learning of objects
We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and increm...
Gespeichert in:
| Veröffentlicht in: | Neural networks 2008, Vol.21 (1), p.65-77 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 77 |
|---|---|
| container_issue | 1 |
| container_start_page | 65 |
| container_title | Neural networks |
| container_volume | 21 |
| creator | Kirstein, Stephan Wersing, Heiko Körner, Edgar |
| description | We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours. |
| doi_str_mv | 10.1016/j.neunet.2007.10.005 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_70353675</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0893608007002043</els_id><sourcerecordid>19410948</sourcerecordid><originalsourceid>FETCH-LOGICAL-c467t-2b24cb0c69db352203dcc9138ca46424860795f163aabe126de83335c4fcab7c3</originalsourceid><addsrcrecordid>eNqFkE1r3DAQhkVpabZp_0EpurQ3b0YfluRLIYT0AwKBkJ6FLI9TLbKVSvbC_vtq2aW9taeB4XlfZh5C3jPYMmDqaredcZ1x2XIAXVdbgPYF2TCju4Zrw1-SDZhONAoMXJA3pewAQBkpXpMLZpjhXKsNebimfUgxPQXvYjzQKS1h7xYc6D6U1UU64ZTygbrsf4YF_bJmpGPKNM0xzEgjujyH-YmmkaZ-V4HylrwaXSz47jwvyY8vt48335q7-6_fb67vGi-VXhrec-l78KobetFyDmLwvmPCeCeV5NIo0F07MiWc65FxNaARQrRejt712otL8unU-5zTrxXLYqdQPMboZkxrsRpEK5Ru_wuyTjLopKmgPIE-p1IyjvY5h8nlg2Vgj9Ltzp6k26P047ZKr7EP5_61n3D4GzpbrsDHM-BK1TxmN_tQ_nAcmKiP68p9PnFYte0DZlt8wNnjEHI1a4cU_n3Jb-Nfok0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>19410948</pqid></control><display><type>article</type><title>A biologically motivated visual memory architecture for online learning of objects</title><source>MEDLINE</source><source>Access via ScienceDirect (Elsevier)</source><creator>Kirstein, Stephan ; Wersing, Heiko ; Körner, Edgar</creator><creatorcontrib>Kirstein, Stephan ; Wersing, Heiko ; Körner, Edgar</creatorcontrib><description>We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/j.neunet.2007.10.005</identifier><identifier>PMID: 18182276</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Algorithms ; Applied sciences ; Artificial intelligence ; Coding, codes ; Computer science; control theory; systems ; Discrimination Learning - physiology ; Exact sciences and technology ; Hierarchical feature extraction ; Humans ; Incremental and life-long learning ; Information, signal and communications theory ; Learning and adaptive systems ; Learning vector quantization ; Memory - physiology ; Models, Neurological ; Motivation ; Neural Networks (Computer) ; Online Systems ; Pattern recognition ; Pattern Recognition, Visual - physiology ; Photic Stimulation ; Sampling, quantization ; Signal and communications theory ; Signal processing ; Stability-plasticity dilemma ; Telecommunications and information theory</subject><ispartof>Neural networks, 2008, Vol.21 (1), p.65-77</ispartof><rights>2007 Elsevier Ltd</rights><rights>2008 INIST-CNRS</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c467t-2b24cb0c69db352203dcc9138ca46424860795f163aabe126de83335c4fcab7c3</citedby><cites>FETCH-LOGICAL-c467t-2b24cb0c69db352203dcc9138ca46424860795f163aabe126de83335c4fcab7c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.neunet.2007.10.005$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,4024,27923,27924,27925,45995</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20139137$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18182276$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kirstein, Stephan</creatorcontrib><creatorcontrib>Wersing, Heiko</creatorcontrib><creatorcontrib>Körner, Edgar</creatorcontrib><title>A biologically motivated visual memory architecture for online learning of objects</title><title>Neural networks</title><addtitle>Neural Netw</addtitle><description>We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours.</description><subject>Algorithms</subject><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Coding, codes</subject><subject>Computer science; control theory; systems</subject><subject>Discrimination Learning - physiology</subject><subject>Exact sciences and technology</subject><subject>Hierarchical feature extraction</subject><subject>Humans</subject><subject>Incremental and life-long learning</subject><subject>Information, signal and communications theory</subject><subject>Learning and adaptive systems</subject><subject>Learning vector quantization</subject><subject>Memory - physiology</subject><subject>Models, Neurological</subject><subject>Motivation</subject><subject>Neural Networks (Computer)</subject><subject>Online Systems</subject><subject>Pattern recognition</subject><subject>Pattern Recognition, Visual - physiology</subject><subject>Photic Stimulation</subject><subject>Sampling, quantization</subject><subject>Signal and communications theory</subject><subject>Signal processing</subject><subject>Stability-plasticity dilemma</subject><subject>Telecommunications and information theory</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFkE1r3DAQhkVpabZp_0EpurQ3b0YfluRLIYT0AwKBkJ6FLI9TLbKVSvbC_vtq2aW9taeB4XlfZh5C3jPYMmDqaredcZ1x2XIAXVdbgPYF2TCju4Zrw1-SDZhONAoMXJA3pewAQBkpXpMLZpjhXKsNebimfUgxPQXvYjzQKS1h7xYc6D6U1UU64ZTygbrsf4YF_bJmpGPKNM0xzEgjujyH-YmmkaZ-V4HylrwaXSz47jwvyY8vt48335q7-6_fb67vGi-VXhrec-l78KobetFyDmLwvmPCeCeV5NIo0F07MiWc65FxNaARQrRejt712otL8unU-5zTrxXLYqdQPMboZkxrsRpEK5Ru_wuyTjLopKmgPIE-p1IyjvY5h8nlg2Vgj9Ltzp6k26P047ZKr7EP5_61n3D4GzpbrsDHM-BK1TxmN_tQ_nAcmKiP68p9PnFYte0DZlt8wNnjEHI1a4cU_n3Jb-Nfok0</recordid><startdate>2008</startdate><enddate>2008</enddate><creator>Kirstein, Stephan</creator><creator>Wersing, Heiko</creator><creator>Körner, Edgar</creator><general>Elsevier Ltd</general><general>Elsevier Science</general><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>7QO</scope><scope>7TK</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>2008</creationdate><title>A biologically motivated visual memory architecture for online learning of objects</title><author>Kirstein, Stephan ; Wersing, Heiko ; Körner, Edgar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c467t-2b24cb0c69db352203dcc9138ca46424860795f163aabe126de83335c4fcab7c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Algorithms</topic><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Coding, codes</topic><topic>Computer science; control theory; systems</topic><topic>Discrimination Learning - physiology</topic><topic>Exact sciences and technology</topic><topic>Hierarchical feature extraction</topic><topic>Humans</topic><topic>Incremental and life-long learning</topic><topic>Information, signal and communications theory</topic><topic>Learning and adaptive systems</topic><topic>Learning vector quantization</topic><topic>Memory - physiology</topic><topic>Models, Neurological</topic><topic>Motivation</topic><topic>Neural Networks (Computer)</topic><topic>Online Systems</topic><topic>Pattern recognition</topic><topic>Pattern Recognition, Visual - physiology</topic><topic>Photic Stimulation</topic><topic>Sampling, quantization</topic><topic>Signal and communications theory</topic><topic>Signal processing</topic><topic>Stability-plasticity dilemma</topic><topic>Telecommunications and information theory</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kirstein, Stephan</creatorcontrib><creatorcontrib>Wersing, Heiko</creatorcontrib><creatorcontrib>Körner, Edgar</creatorcontrib><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>Biotechnology Research Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kirstein, Stephan</au><au>Wersing, Heiko</au><au>Körner, Edgar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A biologically motivated visual memory architecture for online learning of objects</atitle><jtitle>Neural networks</jtitle><addtitle>Neural Netw</addtitle><date>2008</date><risdate>2008</risdate><volume>21</volume><issue>1</issue><spage>65</spage><epage>77</epage><pages>65-77</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><abstract>We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><pmid>18182276</pmid><doi>10.1016/j.neunet.2007.10.005</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0893-6080 |
| ispartof | Neural networks, 2008, Vol.21 (1), p.65-77 |
| issn | 0893-6080 1879-2782 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_70353675 |
| source | MEDLINE; Access via ScienceDirect (Elsevier) |
| subjects | Algorithms Applied sciences Artificial intelligence Coding, codes Computer science control theory systems Discrimination Learning - physiology Exact sciences and technology Hierarchical feature extraction Humans Incremental and life-long learning Information, signal and communications theory Learning and adaptive systems Learning vector quantization Memory - physiology Models, Neurological Motivation Neural Networks (Computer) Online Systems Pattern recognition Pattern Recognition, Visual - physiology Photic Stimulation Sampling, quantization Signal and communications theory Signal processing Stability-plasticity dilemma Telecommunications and information theory |
| title | A biologically motivated visual memory architecture for online learning of objects |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T12%3A53%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20biologically%20motivated%20visual%20memory%20architecture%20for%20online%20learning%20of%20objects&rft.jtitle=Neural%20networks&rft.au=Kirstein,%20Stephan&rft.date=2008&rft.volume=21&rft.issue=1&rft.spage=65&rft.epage=77&rft.pages=65-77&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/j.neunet.2007.10.005&rft_dat=%3Cproquest_cross%3E19410948%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=19410948&rft_id=info:pmid/18182276&rft_els_id=S0893608007002043&rfr_iscdi=true |