Event boards as tools for holistic AI

Gärdenfors, P; Williams, MA; Johnston, B; Billingsley, R; Vitale, J; Peppas, P; Clark, J

Event boards as tools for holistic AI

Gärdenfors, P Williams, MA

Johnston, B Billingsley, R Vitale, J

Peppas, P

Clark, J

Permalink

Publication Type:: Conference Proceeding
Citation:: CEUR Workshop Proceedings, 2019, 2418 pp. 1 - 10
Issue Date:: 2019-01-01

Closed Access

	Filename	Description	Size
	Event boards 8 (3).pdf	Published version	271.01 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Gärdenfors, P	en_US
dc.contributor.author	Williams, MA https://orcid.org/0000-0002-1047-0503	en_US
dc.contributor.author	Johnston, B	en_US
dc.contributor.author	Billingsley, R	en_US
dc.contributor.author	Vitale, J https://orcid.org/0000-0001-6099-675X	en_US
dc.contributor.author	Peppas, P https://orcid.org/0000-0002-0008-5505	en_US
dc.contributor.author	Clark, J https://orcid.org/0000-0002-1920-341X	en_US
dc.date.issued	2019-01-01	en_US
dc.identifier.citation	CEUR Workshop Proceedings, 2019, 2418 pp. 1 - 10	en_US
dc.identifier.issn	1613-0073	en_US
dc.identifier.uri	http://hdl.handle.net/10453/131598
dc.description.abstract	© 2019 CEUR-WS. All rights reserved. We propose a novel architecture for holistic AI systems that integrate machine learning and knowledge representation. We extend an earlier proposal to divide representations into symbolic, conceptual and subconceptual levels. The key idea is to use event boards representing components of events as an analogy to blackboards found in earlier AI systems. The event components are ‘thematic roles’ such as agent, patient, recipient, action, and result. They are represented in terms of vectors of conceptual spaces rather than in symbolic form that has been used previously. A control level, including an attention mechanism decides which processes are run.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP160102693
dc.relation.ispartof	CEUR Workshop Proceedings	en_US
dc.title	Event boards as tools for holistic AI	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2418	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Software
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	2418	en_US

Abstract:

© 2019 CEUR-WS. All rights reserved. We propose a novel architecture for holistic AI systems that integrate machine learning and knowledge representation. We extend an earlier proposal to divide representations into symbolic, conceptual and subconceptual levels. The key idea is to use event boards representing components of events as an analogy to blackboards found in earlier AI systems. The event components are ‘thematic roles’ such as agent, patient, recipient, action, and result. They are represented in terms of vectors of conceptual spaces rather than in symbolic form that has been used previously. A control level, including an attention mechanism decides which processes are run.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/131598