Neuro-symbolic AI (original) (raw)
Neuro-symbolic AI integrates neural and symbolic AI architectures to address complementary strengths and weaknesses of each, providing a robust AI capable of reasoning, learning, and cognitive modeling. As argued by Valiant and many others, the effective construction of rich computational cognitive models demands the combination of sound symbolic reasoning and efficient machine learning models. Gary Marcus, argues that: "We cannot construct rich cognitive models in an adequate, automated way without the triumvirate of hybrid architecture, rich prior knowledge, and sophisticated techniques for reasoning.". Further, "To build a robust, knowledge-driven approach to AI we must have the machinery of symbol-manipulation in our toolkit. Too much of useful knowledge is abstract to make do without
| Property | Value |
|---|---|
| dbo:abstract | Neuro-symbolic AI integrates neural and symbolic AI architectures to address complementary strengths and weaknesses of each, providing a robust AI capable of reasoning, learning, and cognitive modeling. As argued by Valiant and many others, the effective construction of rich computational cognitive models demands the combination of sound symbolic reasoning and efficient machine learning models. Gary Marcus, argues that: "We cannot construct rich cognitive models in an adequate, automated way without the triumvirate of hybrid architecture, rich prior knowledge, and sophisticated techniques for reasoning.". Further, "To build a robust, knowledge-driven approach to AI we must have the machinery of symbol-manipulation in our toolkit. Too much of useful knowledge is abstract to make do without tools that represent and manipulate abstraction, and to date, the only machinery that we know of that can manipulate such abstract knowledge reliably is the apparatus of symbol-manipulation." Henry Kautz, Francesca Rossi, and Bart Selman have also argued for a synthesis. Their arguments are based on a need to address the two kinds of thinking discussed in Daniel Kahneman's book, Thinking Fast and Slow. Kahneman describes human thinking as having two components, System 1 and System 2. System 1 is fast, automatic, intuitive and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is used for pattern recognition. System 2 handles planning, deduction, and deliberative thinking. In this view, deep learning best handles the first kind of cognition while symbolic reasoning best handles the second kind. Both are needed for a robust, reliable AI that can learn, reason, and interact with humans to accept advice and answer questions. (en) |
| dbo:wikiPageExternalLink | https://aaai-2022.virtualchair.net/plenary_13.html https://ojs.aaai.org/index.php/aimagazine/article/view/19122 https://aaai-2022.virtualchair.net/plenary_2.html https://www.youtube.com/watch%3Fv=_cQITY0SPiw https://www.aaai.org/ocs/index.php/SSS/SSS15/paper/viewFile/10281/10029 https://people.cs.ksu.edu/~hitzler/nesy |
| dbo:wikiPageID | 66170649 (xsd:integer) |
| dbo:wikiPageLength | 12875 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1124355243 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:ProbLog dbr:Bart_Selman dbr:Deep_learning dbc:Artificial_intelligence dbr:Thinking,_Fast_and_Slow dbr:Gary_Marcus dbr:Monte_Carlo_tree_search dbr:Connectionism dbr:Leslie_Valiant dbr:Machine_learning dbr:Macsyma dbr:GPT-3 dbr:Daniel_Kahneman dbr:AlphaGo dbr:Francesca_Rossi dbr:And–or_tree dbr:Henry_Kautz dbr:Symbolic_artificial_intelligence dbr:Cognitive_model dbr:BERT_(language_model) dbr:Knowledge_bases dbr:Symbolic_AI dbr:Cognitive_models dbr:Thinking_Fast_and_Slow dbr:Connectionist_AI |
| dbp:wikiPageUsesTemplate | dbt:Cite_AV_media dbt:Cite_arXiv dbt:Cite_book dbt:Cite_conference dbt:Cite_journal dbt:Cite_web dbt:Reflist dbt:Sfn dbt:Short_description dbt:Copy_edit |
| dcterms:subject | dbc:Artificial_intelligence |
| rdfs:comment | Neuro-symbolic AI integrates neural and symbolic AI architectures to address complementary strengths and weaknesses of each, providing a robust AI capable of reasoning, learning, and cognitive modeling. As argued by Valiant and many others, the effective construction of rich computational cognitive models demands the combination of sound symbolic reasoning and efficient machine learning models. Gary Marcus, argues that: "We cannot construct rich cognitive models in an adequate, automated way without the triumvirate of hybrid architecture, rich prior knowledge, and sophisticated techniques for reasoning.". Further, "To build a robust, knowledge-driven approach to AI we must have the machinery of symbol-manipulation in our toolkit. Too much of useful knowledge is abstract to make do without (en) |
| rdfs:label | Neuro-symbolic AI (en) |
| owl:sameAs | wikidata:Neuro-symbolic AI https://global.dbpedia.org/id/GQGju |
| prov:wasDerivedFrom | wikipedia-en:Neuro-symbolic_AI?oldid=1124355243&ns=0 |
| foaf:isPrimaryTopicOf | wikipedia-en:Neuro-symbolic_AI |
| is dbo:wikiPageRedirects of | dbr:Neurosymbolic_AI |
| is dbo:wikiPageWikiLink of | dbr:GOFAI dbr:Hybrid_intelligent_system dbr:Symbolic_artificial_intelligence dbr:Neurosymbolic_AI |
| is foaf:primaryTopic of | wikipedia-en:Neuro-symbolic_AI |