Neurosymbolic Artificial Intelligence (Why, What, and How)
Humans interact with the environment using a combination of perception-transforming sensory inputs from their environment into symbols, and cognition-mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired...
Gespeichert in:
Veröffentlicht in: | IEEE intelligent systems 2023-05, Vol.38 (3), p.56-62 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 62 |
---|---|
container_issue | 3 |
container_start_page | 56 |
container_title | IEEE intelligent systems |
container_volume | 38 |
creator | Sheth, Amit Roy, Kaushik Gaur, Manas Sheth, Amit |
description | Humans interact with the environment using a combination of perception-transforming sensory inputs from their environment into symbols, and cognition-mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of artificial intelligence (AI), refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision making in safety-critical applications such as health care, criminal justice, and autonomous driving. |
doi_str_mv | 10.1109/MIS.2023.3268724 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_MIS_2023_3268724</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10148662</ieee_id><sourcerecordid>2825602850</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-b17fb7255092a89cf2fbcbaaa5db0cc57b25de59ec8662c75677effbf7c81d993</originalsourceid><addsrcrecordid>eNpNkD1PwzAQhi0EEqWwMzBEYgGpKfYljm22qgJaqcAAqKNlOzZ1lSbFSYX673HUDkx3w_Pex4PQNcFjQrB4eJ1_jAFDNs6g4AzyEzQgIicpAZGfxp72fcHgHF207RpHEhM-QI9vdheadr_RTeVNMgmdd954VSXzurNV5b9tbWxyt1ztR8lypbpRouoymTW_95fozKmqtVfHOkRfz0-f01m6eH-ZTyeL1ICALtWEOc2AUixAcWEcOG20UoqWGhtDmQZaWiqs4UUBhtGCMeucdsxwUgqRDdHtYe42ND8723Zy3exCHVdK4EALDJziSOEDZeI7bbBOboPfqLCXBMvekIyGZG9IHg3FyM0h4q21_3CS95dkfyjpYQw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2825602850</pqid></control><display><type>article</type><title>Neurosymbolic Artificial Intelligence (Why, What, and How)</title><source>IEEE Electronic Library (IEL)</source><creator>Sheth, Amit ; Roy, Kaushik ; Gaur, Manas ; Sheth, Amit</creator><contributor>Amit Sheth</contributor><creatorcontrib>Sheth, Amit ; Roy, Kaushik ; Gaur, Manas ; Sheth, Amit ; Amit Sheth</creatorcontrib><description>Humans interact with the environment using a combination of perception-transforming sensory inputs from their environment into symbols, and cognition-mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of artificial intelligence (AI), refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision making in safety-critical applications such as health care, criminal justice, and autonomous driving.</description><identifier>ISSN: 1541-1672</identifier><identifier>EISSN: 1941-1294</identifier><identifier>DOI: 10.1109/MIS.2023.3268724</identifier><identifier>CODEN: IISYF7</identifier><language>eng</language><publisher>Los Alamitos: IEEE</publisher><subject>Artificial intelligence ; Cognition ; Decision making ; Human factors ; Machine learning ; Medical services ; Neural networks ; Object recognition ; Pattern recognition ; Perception ; Reasoning ; Safety ; Safety critical ; Self-supervised learning ; Symbols</subject><ispartof>IEEE intelligent systems, 2023-05, Vol.38 (3), p.56-62</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-b17fb7255092a89cf2fbcbaaa5db0cc57b25de59ec8662c75677effbf7c81d993</citedby><cites>FETCH-LOGICAL-c292t-b17fb7255092a89cf2fbcbaaa5db0cc57b25de59ec8662c75677effbf7c81d993</cites><orcidid>0000-0001-6610-7845 ; 0000-0002-0021-5293 ; 0000-0002-5411-2230</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10148662$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10148662$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><contributor>Amit Sheth</contributor><creatorcontrib>Sheth, Amit</creatorcontrib><creatorcontrib>Roy, Kaushik</creatorcontrib><creatorcontrib>Gaur, Manas</creatorcontrib><creatorcontrib>Sheth, Amit</creatorcontrib><title>Neurosymbolic Artificial Intelligence (Why, What, and How)</title><title>IEEE intelligent systems</title><addtitle>MIS</addtitle><description>Humans interact with the environment using a combination of perception-transforming sensory inputs from their environment into symbols, and cognition-mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of artificial intelligence (AI), refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision making in safety-critical applications such as health care, criminal justice, and autonomous driving.</description><subject>Artificial intelligence</subject><subject>Cognition</subject><subject>Decision making</subject><subject>Human factors</subject><subject>Machine learning</subject><subject>Medical services</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Pattern recognition</subject><subject>Perception</subject><subject>Reasoning</subject><subject>Safety</subject><subject>Safety critical</subject><subject>Self-supervised learning</subject><subject>Symbols</subject><issn>1541-1672</issn><issn>1941-1294</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkD1PwzAQhi0EEqWwMzBEYgGpKfYljm22qgJaqcAAqKNlOzZ1lSbFSYX673HUDkx3w_Pex4PQNcFjQrB4eJ1_jAFDNs6g4AzyEzQgIicpAZGfxp72fcHgHF207RpHEhM-QI9vdheadr_RTeVNMgmdd954VSXzurNV5b9tbWxyt1ztR8lypbpRouoymTW_95fozKmqtVfHOkRfz0-f01m6eH-ZTyeL1ICALtWEOc2AUixAcWEcOG20UoqWGhtDmQZaWiqs4UUBhtGCMeucdsxwUgqRDdHtYe42ND8723Zy3exCHVdK4EALDJziSOEDZeI7bbBOboPfqLCXBMvekIyGZG9IHg3FyM0h4q21_3CS95dkfyjpYQw</recordid><startdate>20230501</startdate><enddate>20230501</enddate><creator>Sheth, Amit</creator><creator>Roy, Kaushik</creator><creator>Gaur, Manas</creator><creator>Sheth, Amit</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-6610-7845</orcidid><orcidid>https://orcid.org/0000-0002-0021-5293</orcidid><orcidid>https://orcid.org/0000-0002-5411-2230</orcidid></search><sort><creationdate>20230501</creationdate><title>Neurosymbolic Artificial Intelligence (Why, What, and How)</title><author>Sheth, Amit ; Roy, Kaushik ; Gaur, Manas ; Sheth, Amit</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-b17fb7255092a89cf2fbcbaaa5db0cc57b25de59ec8662c75677effbf7c81d993</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Cognition</topic><topic>Decision making</topic><topic>Human factors</topic><topic>Machine learning</topic><topic>Medical services</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Pattern recognition</topic><topic>Perception</topic><topic>Reasoning</topic><topic>Safety</topic><topic>Safety critical</topic><topic>Self-supervised learning</topic><topic>Symbols</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sheth, Amit</creatorcontrib><creatorcontrib>Roy, Kaushik</creatorcontrib><creatorcontrib>Gaur, Manas</creatorcontrib><creatorcontrib>Sheth, Amit</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>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Library & Information Sciences Abstracts (LISA)</collection><collection>Library & Information Science Abstracts (LISA)</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE intelligent systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sheth, Amit</au><au>Roy, Kaushik</au><au>Gaur, Manas</au><au>Sheth, Amit</au><au>Amit Sheth</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Neurosymbolic Artificial Intelligence (Why, What, and How)</atitle><jtitle>IEEE intelligent systems</jtitle><stitle>MIS</stitle><date>2023-05-01</date><risdate>2023</risdate><volume>38</volume><issue>3</issue><spage>56</spage><epage>62</epage><pages>56-62</pages><issn>1541-1672</issn><eissn>1941-1294</eissn><coden>IISYF7</coden><abstract>Humans interact with the environment using a combination of perception-transforming sensory inputs from their environment into symbols, and cognition-mapping symbols to knowledge about the environment for supporting abstraction, reasoning by analogy, and long-term planning. Human perception-inspired machine perception, in the context of artificial intelligence (AI), refers to large-scale pattern recognition from raw data using neural networks trained using self-supervised learning objectives such as next-word prediction or object recognition. On the other hand, machine cognition encompasses more complex computations, such as using knowledge of the environment to guide reasoning, analogy, and long-term planning. Humans can also control and explain their cognitive functions. This seems to require the retention of symbolic mappings from perception outputs to knowledge about their environment. For example, humans can follow and explain the guidelines and safety constraints driving their decision making in safety-critical applications such as health care, criminal justice, and autonomous driving.</abstract><cop>Los Alamitos</cop><pub>IEEE</pub><doi>10.1109/MIS.2023.3268724</doi><tpages>7</tpages><orcidid>https://orcid.org/0000-0001-6610-7845</orcidid><orcidid>https://orcid.org/0000-0002-0021-5293</orcidid><orcidid>https://orcid.org/0000-0002-5411-2230</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1541-1672 |
ispartof | IEEE intelligent systems, 2023-05, Vol.38 (3), p.56-62 |
issn | 1541-1672 1941-1294 |
language | eng |
recordid | cdi_crossref_primary_10_1109_MIS_2023_3268724 |
source | IEEE Electronic Library (IEL) |
subjects | Artificial intelligence Cognition Decision making Human factors Machine learning Medical services Neural networks Object recognition Pattern recognition Perception Reasoning Safety Safety critical Self-supervised learning Symbols |
title | Neurosymbolic Artificial Intelligence (Why, What, and How) |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A58%3A01IST&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=Neurosymbolic%20Artificial%20Intelligence%20(Why,%20What,%20and%20How)&rft.jtitle=IEEE%20intelligent%20systems&rft.au=Sheth,%20Amit&rft.date=2023-05-01&rft.volume=38&rft.issue=3&rft.spage=56&rft.epage=62&rft.pages=56-62&rft.issn=1541-1672&rft.eissn=1941-1294&rft.coden=IISYF7&rft_id=info:doi/10.1109/MIS.2023.3268724&rft_dat=%3Cproquest_RIE%3E2825602850%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=2825602850&rft_id=info:pmid/&rft_ieee_id=10148662&rfr_iscdi=true |