liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Stimulus Equivalence in NARS
Linköping University, Department of Computer and Information Science, Human-Centered Systems. Linköping University, Faculty of Science & Engineering. Stockholm Univ, Sweden.ORCID iD: 0000-0001-5547-3866
Stockholm Univ, Sweden.
2023 (English)In: ARTIFICIAL GENERAL INTELLIGENCE, AGI 2023, SPRINGER INTERNATIONAL PUBLISHING AG , 2023, Vol. 13921, p. 158-166Conference paper, Published paper (Refereed)
Abstract [en]

Stimulus equivalence is the ability to act as if two objects are identical, despite no shared properties. This ability is hypothesized to be the foundation for symbolic reasoning and the development of language. It is believed to be unique to humans and not present in other animals. Stimulus equivalence can be studied in the context of a matching-to-sample experimental task, by demonstrating a combination of symmetrical and transitive performances. This study aimed to explore stimulus equivalence with the Non-Axiomatic Reasoning System (NARS). More specifically, we propose two new capabilities for OpenNARS for Applications (ONA) - contingency entailment and acquired relations. We provide an explanation how this would lead to ONA being able to learn symmetrical and transitive performances leading to full stimulus equivalence.

Place, publisher, year, edition, pages
SPRINGER INTERNATIONAL PUBLISHING AG , 2023. Vol. 13921, p. 158-166
Series
Lecture Notes in Artificial Intelligence, ISSN 2945-9133
Keywords [en]
Stimulus equivalence; Symbolic reasoning; NARS
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-209120DOI: 10.1007/978-3-031-33469-6_16ISI: 001319411700016ISBN: 9783031334689 (print)ISBN: 9783031334696 (electronic)OAI: oai:DiVA.org:liu-209120DiVA, id: diva2:1910914
Conference
16th International Conference on Artificial General Intelligence (AGI), Royal Inst Technol, Stockholm, SWEDEN, jun 16-19, 2023
Available from: 2024-11-06 Created: 2024-11-06 Last updated: 2024-11-06

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Johansson, Robert
By organisation
Human-Centered SystemsFaculty of Science & Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 56 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf