Abductive reasoning with recurrent neural networks
Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on...
Gespeichert in:
Veröffentlicht in: | Neural networks 2003-06, Vol.16 (5), p.665-673 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 673 |
---|---|
container_issue | 5 |
container_start_page | 665 |
container_title | Neural networks |
container_volume | 16 |
creator | Abdelbar, Ashraf M. Andrews, Emad A.M. Wunsch, Donald C. |
description | Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method. |
doi_str_mv | 10.1016/S0893-6080(03)00114-X |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_73454542</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S089360800300114X</els_id><sourcerecordid>73454542</sourcerecordid><originalsourceid>FETCH-LOGICAL-c420t-c996d87e195d6efac2696cf13e73734ab4b14ad6bec0d24edf592ee751f74ae3</originalsourceid><addsrcrecordid>eNqFkMlKA0EQhhtRTIw-gpKLoofR6mW2k4TgBgEP5pBb09Ndo62Tmdg9k-Db21kwR6nDT8FXCx8h5xRuKdDk7g2ynEcJZHAN_AaAUhHNDkifZmkesTRjh6T_h_TIifefAJBkgh-THmVZDMBon7BRYTrd2iUOHSrf1LZ-H65s-xFa3TmHdTussXOqCtGuGvflT8lRqSqPZ7sckOnjw3T8HE1en17Go0mkBYM20nmemCxFmscmwVJpluSJLinHlKdcqEIUVCiTFKjBMIGmjHOGmMa0TIVCPiBX27UL13x36Fs5t15jVakam87LsCMOxQIYb0HtGu8dlnLh7Fy5H0lBrl3JjSu5FiGBy40rOQtzF7sDXTFHs5_ayQnA5Q5QXquqdKrW1u85kTMWUxG4-y2HwcbSopNeW6w1GhskttI09p9XfgFjIYZp</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>73454542</pqid></control><display><type>article</type><title>Abductive reasoning with recurrent neural networks</title><source>MEDLINE</source><source>ScienceDirect Journals (5 years ago - present)</source><creator>Abdelbar, Ashraf M. ; Andrews, Emad A.M. ; Wunsch, Donald C.</creator><creatorcontrib>Abdelbar, Ashraf M. ; Andrews, Emad A.M. ; Wunsch, Donald C.</creatorcontrib><description>Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.</description><identifier>ISSN: 0893-6080</identifier><identifier>EISSN: 1879-2782</identifier><identifier>DOI: 10.1016/S0893-6080(03)00114-X</identifier><identifier>PMID: 12850021</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Applied sciences ; Artificial Intelligence ; Computer science; control theory; systems ; Connectionism. Neural networks ; Exact sciences and technology ; Neural Networks (Computer)</subject><ispartof>Neural networks, 2003-06, Vol.16 (5), p.665-673</ispartof><rights>2003 Elsevier Science Ltd</rights><rights>2003 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c420t-c996d87e195d6efac2696cf13e73734ab4b14ad6bec0d24edf592ee751f74ae3</citedby><cites>FETCH-LOGICAL-c420t-c996d87e195d6efac2696cf13e73734ab4b14ad6bec0d24edf592ee751f74ae3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S089360800300114X$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>309,310,314,776,780,785,786,3537,23909,23910,25118,27901,27902,65534</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=14922514$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/12850021$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Abdelbar, Ashraf M.</creatorcontrib><creatorcontrib>Andrews, Emad A.M.</creatorcontrib><creatorcontrib>Wunsch, Donald C.</creatorcontrib><title>Abductive reasoning with recurrent neural networks</title><title>Neural networks</title><addtitle>Neural Netw</addtitle><description>Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.</description><subject>Applied sciences</subject><subject>Artificial Intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Connectionism. Neural networks</subject><subject>Exact sciences and technology</subject><subject>Neural Networks (Computer)</subject><issn>0893-6080</issn><issn>1879-2782</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFkMlKA0EQhhtRTIw-gpKLoofR6mW2k4TgBgEP5pBb09Ndo62Tmdg9k-Db21kwR6nDT8FXCx8h5xRuKdDk7g2ynEcJZHAN_AaAUhHNDkifZmkesTRjh6T_h_TIifefAJBkgh-THmVZDMBon7BRYTrd2iUOHSrf1LZ-H65s-xFa3TmHdTussXOqCtGuGvflT8lRqSqPZ7sckOnjw3T8HE1en17Go0mkBYM20nmemCxFmscmwVJpluSJLinHlKdcqEIUVCiTFKjBMIGmjHOGmMa0TIVCPiBX27UL13x36Fs5t15jVakam87LsCMOxQIYb0HtGu8dlnLh7Fy5H0lBrl3JjSu5FiGBy40rOQtzF7sDXTFHs5_ayQnA5Q5QXquqdKrW1u85kTMWUxG4-y2HwcbSopNeW6w1GhskttI09p9XfgFjIYZp</recordid><startdate>20030601</startdate><enddate>20030601</enddate><creator>Abdelbar, Ashraf M.</creator><creator>Andrews, Emad A.M.</creator><creator>Wunsch, Donald C.</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>7X8</scope></search><sort><creationdate>20030601</creationdate><title>Abductive reasoning with recurrent neural networks</title><author>Abdelbar, Ashraf M. ; Andrews, Emad A.M. ; Wunsch, Donald C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c420t-c996d87e195d6efac2696cf13e73734ab4b14ad6bec0d24edf592ee751f74ae3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Applied sciences</topic><topic>Artificial Intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Connectionism. Neural networks</topic><topic>Exact sciences and technology</topic><topic>Neural Networks (Computer)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Abdelbar, Ashraf M.</creatorcontrib><creatorcontrib>Andrews, Emad A.M.</creatorcontrib><creatorcontrib>Wunsch, Donald C.</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>MEDLINE - Academic</collection><jtitle>Neural networks</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Abdelbar, Ashraf M.</au><au>Andrews, Emad A.M.</au><au>Wunsch, Donald C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Abductive reasoning with recurrent neural networks</atitle><jtitle>Neural networks</jtitle><addtitle>Neural Netw</addtitle><date>2003-06-01</date><risdate>2003</risdate><volume>16</volume><issue>5</issue><spage>665</spage><epage>673</epage><pages>665-673</pages><issn>0893-6080</issn><eissn>1879-2782</eissn><abstract>Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><pmid>12850021</pmid><doi>10.1016/S0893-6080(03)00114-X</doi><tpages>9</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0893-6080 |
ispartof | Neural networks, 2003-06, Vol.16 (5), p.665-673 |
issn | 0893-6080 1879-2782 |
language | eng |
recordid | cdi_proquest_miscellaneous_73454542 |
source | MEDLINE; ScienceDirect Journals (5 years ago - present) |
subjects | Applied sciences Artificial Intelligence Computer science control theory systems Connectionism. Neural networks Exact sciences and technology Neural Networks (Computer) |
title | Abductive reasoning with recurrent neural networks |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-17T00%3A27%3A45IST&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=Abductive%20reasoning%20with%20recurrent%20neural%20networks&rft.jtitle=Neural%20networks&rft.au=Abdelbar,%20Ashraf%20M.&rft.date=2003-06-01&rft.volume=16&rft.issue=5&rft.spage=665&rft.epage=673&rft.pages=665-673&rft.issn=0893-6080&rft.eissn=1879-2782&rft_id=info:doi/10.1016/S0893-6080(03)00114-X&rft_dat=%3Cproquest_cross%3E73454542%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=73454542&rft_id=info:pmid/12850021&rft_els_id=S089360800300114X&rfr_iscdi=true |