A Novel Neural-symbolic System under Statistical Relational Learning

A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-09
Hauptverfasser: Yu, Dongran, Liu, Xueyan, Pan, Shirui, Li, Anchen, Yang, Bo
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Yu, Dongran
Liu, Xueyan
Pan, Shirui
Li, Anchen
Yang, Bo
description A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current approaches in this area have been limited in their combining way, generalization and interpretability. To address these limitations, we propose a general bi-level probabilistic graphical reasoning framework called GBPGR. This framework leverages statistical relational learning to effectively integrate deep learning models and symbolic reasoning in a mutually beneficial manner. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. At the same time, the deep learning models assist in enhancing the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2866253513</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2866253513</sourcerecordid><originalsourceid>FETCH-proquest_journals_28662535133</originalsourceid><addsrcrecordid>eNqNi70KwjAURoMgWLTvEHAutDemdhV_cJAO6l5ivUpKmmhuIvTt7eADOH3nwPkmLAEhiqxaAcxYStTleQ7lGqQUCdtteO0-aHiN0SuT0dDfnNEtvwwUsOfR3tHzS1BBU9CtMvyMZhRnRzyh8lbb54JNH8oQpr-ds-Vhf90es5d374gUms5FPz6ogaosQQpZCPFf9QU1CjqZ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2866253513</pqid></control><display><type>article</type><title>A Novel Neural-symbolic System under Statistical Relational Learning</title><source>Free E- Journals</source><creator>Yu, Dongran ; Liu, Xueyan ; Pan, Shirui ; Li, Anchen ; Yang, Bo</creator><creatorcontrib>Yu, Dongran ; Liu, Xueyan ; Pan, Shirui ; Li, Anchen ; Yang, Bo</creatorcontrib><description>A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current approaches in this area have been limited in their combining way, generalization and interpretability. To address these limitations, we propose a general bi-level probabilistic graphical reasoning framework called GBPGR. This framework leverages statistical relational learning to effectively integrate deep learning models and symbolic reasoning in a mutually beneficial manner. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. At the same time, the deep learning models assist in enhancing the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial intelligence ; Deep learning ; Reasoning ; Statistical analysis</subject><ispartof>arXiv.org, 2023-09</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Yu, Dongran</creatorcontrib><creatorcontrib>Liu, Xueyan</creatorcontrib><creatorcontrib>Pan, Shirui</creatorcontrib><creatorcontrib>Li, Anchen</creatorcontrib><creatorcontrib>Yang, Bo</creatorcontrib><title>A Novel Neural-symbolic System under Statistical Relational Learning</title><title>arXiv.org</title><description>A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current approaches in this area have been limited in their combining way, generalization and interpretability. To address these limitations, we propose a general bi-level probabilistic graphical reasoning framework called GBPGR. This framework leverages statistical relational learning to effectively integrate deep learning models and symbolic reasoning in a mutually beneficial manner. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. At the same time, the deep learning models assist in enhancing the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.</description><subject>Artificial intelligence</subject><subject>Deep learning</subject><subject>Reasoning</subject><subject>Statistical analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi70KwjAURoMgWLTvEHAutDemdhV_cJAO6l5ivUpKmmhuIvTt7eADOH3nwPkmLAEhiqxaAcxYStTleQ7lGqQUCdtteO0-aHiN0SuT0dDfnNEtvwwUsOfR3tHzS1BBU9CtMvyMZhRnRzyh8lbb54JNH8oQpr-ds-Vhf90es5d374gUms5FPz6ogaosQQpZCPFf9QU1CjqZ</recordid><startdate>20230916</startdate><enddate>20230916</enddate><creator>Yu, Dongran</creator><creator>Liu, Xueyan</creator><creator>Pan, Shirui</creator><creator>Li, Anchen</creator><creator>Yang, Bo</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope></search><sort><creationdate>20230916</creationdate><title>A Novel Neural-symbolic System under Statistical Relational Learning</title><author>Yu, Dongran ; Liu, Xueyan ; Pan, Shirui ; Li, Anchen ; Yang, Bo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28662535133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Deep learning</topic><topic>Reasoning</topic><topic>Statistical analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Yu, Dongran</creatorcontrib><creatorcontrib>Liu, Xueyan</creatorcontrib><creatorcontrib>Pan, Shirui</creatorcontrib><creatorcontrib>Li, Anchen</creatorcontrib><creatorcontrib>Yang, Bo</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Dongran</au><au>Liu, Xueyan</au><au>Pan, Shirui</au><au>Li, Anchen</au><au>Yang, Bo</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Novel Neural-symbolic System under Statistical Relational Learning</atitle><jtitle>arXiv.org</jtitle><date>2023-09-16</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current approaches in this area have been limited in their combining way, generalization and interpretability. To address these limitations, we propose a general bi-level probabilistic graphical reasoning framework called GBPGR. This framework leverages statistical relational learning to effectively integrate deep learning models and symbolic reasoning in a mutually beneficial manner. In GBPGR, the results of symbolic reasoning are utilized to refine and correct the predictions made by the deep learning models. At the same time, the deep learning models assist in enhancing the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in both transductive and inductive tasks.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2866253513
source Free E- Journals
subjects Artificial intelligence
Deep learning
Reasoning
Statistical analysis
title A Novel Neural-symbolic System under Statistical Relational Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T21%3A50%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20Novel%20Neural-symbolic%20System%20under%20Statistical%20Relational%20Learning&rft.jtitle=arXiv.org&rft.au=Yu,%20Dongran&rft.date=2023-09-16&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2866253513%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2866253513&rft_id=info:pmid/&rfr_iscdi=true