Reasoning and Learning About Past Temporal Knowledge in Connectionist Models
The integration of logic-based inference systems and connectionist learning architectures may lead to the construction of semantically sound cognitive models in artificial intelligence. The use of hybrid systems has shown promising results as regards the computation and learning of classical reasoni...
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 | 1493 |
|---|---|
| container_issue | |
| container_start_page | 1488 |
| container_title | |
| container_volume | |
| creator | Borges, R.V. Lamb, L.C. d'Avila Garcez, A.S. |
| description | The integration of logic-based inference systems and connectionist learning architectures may lead to the construction of semantically sound cognitive models in artificial intelligence. The use of hybrid systems has shown promising results as regards the computation and learning of classical reasoning within neural networks. However, there still remains a number of open research issues on the integration of non-classical logics and neural networks. We present a new model for integrating symbolic reasoning about past temporal information and neural learning systems. We propose algorithms that translate background knowledge into a neural network and analyse the effectiveness of learning algorithms when subject to symbolic temporal knowledge. This opens several interesting research paths with possible applications to agents' decision making, cognitive modelling and knowledge-based systems. |
| doi_str_mv | 10.1109/IJCNN.2007.4371178 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4371178</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4371178</ieee_id><sourcerecordid>4371178</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-6b1c6c64e38e15de91c5cc769f5f4749ec36211f8cdc67e290a2858aeff577bf3</originalsourceid><addsrcrecordid>eNo1kMtOwzAURM1Loi39Adj4BxJ8bcePZRXxKISCUJHYVY5zXQWlTpUEIf6eCsJqNDozsxhCLoGlAMxeLx_y1SrljOlUCg2gzRGZguRSgjDs_ZhMOChIpGT6hMytNiPT1p7-M2HFOZn2_QdjXFgrJqR4Rde3sY5b6mJFC3Tdr1mU7edAX1w_0DXu9m3nGvoY268Gqy3SOtK8jRH9UB-6h8xTW2HTX5Cz4Joe56POyNvtzTq_T4rnu2W-KJIadDYkqgSvvJIoDEJWoQWfea-VDVmQWlr0QnGAYHzllUZumeMmMw5DyLQug5iRq7_dGhE3-67eue57M74ifgAKsFKU</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Reasoning and Learning About Past Temporal Knowledge in Connectionist Models</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Borges, R.V. ; Lamb, L.C. ; d'Avila Garcez, A.S.</creator><creatorcontrib>Borges, R.V. ; Lamb, L.C. ; d'Avila Garcez, A.S.</creatorcontrib><description>The integration of logic-based inference systems and connectionist learning architectures may lead to the construction of semantically sound cognitive models in artificial intelligence. The use of hybrid systems has shown promising results as regards the computation and learning of classical reasoning within neural networks. However, there still remains a number of open research issues on the integration of non-classical logics and neural networks. We present a new model for integrating symbolic reasoning about past temporal information and neural learning systems. We propose algorithms that translate background knowledge into a neural network and analyse the effectiveness of learning algorithms when subject to symbolic temporal knowledge. This opens several interesting research paths with possible applications to agents' decision making, cognitive modelling and knowledge-based systems.</description><identifier>ISSN: 2161-4393</identifier><identifier>ISBN: 9781424413799</identifier><identifier>ISBN: 1424413796</identifier><identifier>EISSN: 2161-4407</identifier><identifier>EISBN: 142441380X</identifier><identifier>EISBN: 9781424413805</identifier><identifier>DOI: 10.1109/IJCNN.2007.4371178</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Artificial intelligence ; Artificial neural networks ; Computer architecture ; Computer networks ; Decision making ; Knowledge based systems ; Learning systems ; Logic ; Neural networks</subject><ispartof>2007 International Joint Conference on Neural Networks, 2007, p.1488-1493</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/4371178$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4371178$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Borges, R.V.</creatorcontrib><creatorcontrib>Lamb, L.C.</creatorcontrib><creatorcontrib>d'Avila Garcez, A.S.</creatorcontrib><title>Reasoning and Learning About Past Temporal Knowledge in Connectionist Models</title><title>2007 International Joint Conference on Neural Networks</title><addtitle>IJCNN</addtitle><description>The integration of logic-based inference systems and connectionist learning architectures may lead to the construction of semantically sound cognitive models in artificial intelligence. The use of hybrid systems has shown promising results as regards the computation and learning of classical reasoning within neural networks. However, there still remains a number of open research issues on the integration of non-classical logics and neural networks. We present a new model for integrating symbolic reasoning about past temporal information and neural learning systems. We propose algorithms that translate background knowledge into a neural network and analyse the effectiveness of learning algorithms when subject to symbolic temporal knowledge. This opens several interesting research paths with possible applications to agents' decision making, cognitive modelling and knowledge-based systems.</description><subject>Algorithm design and analysis</subject><subject>Artificial intelligence</subject><subject>Artificial neural networks</subject><subject>Computer architecture</subject><subject>Computer networks</subject><subject>Decision making</subject><subject>Knowledge based systems</subject><subject>Learning systems</subject><subject>Logic</subject><subject>Neural networks</subject><issn>2161-4393</issn><issn>2161-4407</issn><isbn>9781424413799</isbn><isbn>1424413796</isbn><isbn>142441380X</isbn><isbn>9781424413805</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kMtOwzAURM1Loi39Adj4BxJ8bcePZRXxKISCUJHYVY5zXQWlTpUEIf6eCsJqNDozsxhCLoGlAMxeLx_y1SrljOlUCg2gzRGZguRSgjDs_ZhMOChIpGT6hMytNiPT1p7-M2HFOZn2_QdjXFgrJqR4Rde3sY5b6mJFC3Tdr1mU7edAX1w_0DXu9m3nGvoY268Gqy3SOtK8jRH9UB-6h8xTW2HTX5Cz4Joe56POyNvtzTq_T4rnu2W-KJIadDYkqgSvvJIoDEJWoQWfea-VDVmQWlr0QnGAYHzllUZumeMmMw5DyLQug5iRq7_dGhE3-67eue57M74ifgAKsFKU</recordid><startdate>200708</startdate><enddate>200708</enddate><creator>Borges, R.V.</creator><creator>Lamb, L.C.</creator><creator>d'Avila Garcez, A.S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200708</creationdate><title>Reasoning and Learning About Past Temporal Knowledge in Connectionist Models</title><author>Borges, R.V. ; Lamb, L.C. ; d'Avila Garcez, A.S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-6b1c6c64e38e15de91c5cc769f5f4749ec36211f8cdc67e290a2858aeff577bf3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Algorithm design and analysis</topic><topic>Artificial intelligence</topic><topic>Artificial neural networks</topic><topic>Computer architecture</topic><topic>Computer networks</topic><topic>Decision making</topic><topic>Knowledge based systems</topic><topic>Learning systems</topic><topic>Logic</topic><topic>Neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Borges, R.V.</creatorcontrib><creatorcontrib>Lamb, L.C.</creatorcontrib><creatorcontrib>d'Avila Garcez, A.S.</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>Borges, R.V.</au><au>Lamb, L.C.</au><au>d'Avila Garcez, A.S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Reasoning and Learning About Past Temporal Knowledge in Connectionist Models</atitle><btitle>2007 International Joint Conference on Neural Networks</btitle><stitle>IJCNN</stitle><date>2007-08</date><risdate>2007</risdate><spage>1488</spage><epage>1493</epage><pages>1488-1493</pages><issn>2161-4393</issn><eissn>2161-4407</eissn><isbn>9781424413799</isbn><isbn>1424413796</isbn><eisbn>142441380X</eisbn><eisbn>9781424413805</eisbn><abstract>The integration of logic-based inference systems and connectionist learning architectures may lead to the construction of semantically sound cognitive models in artificial intelligence. The use of hybrid systems has shown promising results as regards the computation and learning of classical reasoning within neural networks. However, there still remains a number of open research issues on the integration of non-classical logics and neural networks. We present a new model for integrating symbolic reasoning about past temporal information and neural learning systems. We propose algorithms that translate background knowledge into a neural network and analyse the effectiveness of learning algorithms when subject to symbolic temporal knowledge. This opens several interesting research paths with possible applications to agents' decision making, cognitive modelling and knowledge-based systems.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN.2007.4371178</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2161-4393 |
| ispartof | 2007 International Joint Conference on Neural Networks, 2007, p.1488-1493 |
| issn | 2161-4393 2161-4407 |
| language | eng |
| recordid | cdi_ieee_primary_4371178 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Algorithm design and analysis Artificial intelligence Artificial neural networks Computer architecture Computer networks Decision making Knowledge based systems Learning systems Logic Neural networks |
| title | Reasoning and Learning About Past Temporal Knowledge in Connectionist Models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T21%3A02%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=Reasoning%20and%20Learning%20About%20Past%20Temporal%20Knowledge%20in%20Connectionist%20Models&rft.btitle=2007%20International%20Joint%20Conference%20on%20Neural%20Networks&rft.au=Borges,%20R.V.&rft.date=2007-08&rft.spage=1488&rft.epage=1493&rft.pages=1488-1493&rft.issn=2161-4393&rft.eissn=2161-4407&rft.isbn=9781424413799&rft.isbn_list=1424413796&rft_id=info:doi/10.1109/IJCNN.2007.4371178&rft_dat=%3Cieee_6IE%3E4371178%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=142441380X&rft.eisbn_list=9781424413805&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4371178&rfr_iscdi=true |