Event Boards as Tools for Holistic AI

Peter Gärdenfors; Mary-Anne Williams; Benjamin Johnston; Richard Billingsley; Jonathan Vitale; Pavlos Peppas; Jesse Clark

Event Boards as Tools for Holistic AI

Peter Gärdenfors, Mary-Anne Williams, Benjamin Johnston, Richard Billingsley, Jonathan Vitale, Pavlos Peppas, Jesse Clark

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

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.

Original language	English
Title of host publication	Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition
Place of Publication	Italy
Publisher	DBLP computer science bibliography
Pages	1-10
Number of pages	10
Publication status	Published - 2018
Externally published	Yes
Event	International Workshop on Artificial Intelligence and Cognition - Palermo, Italy Duration: 2 Jul 2018 → 4 Jul 2018

Conference

Conference	International Workshop on Artificial Intelligence and Cognition
Country/Territory	Italy
City	Palermo
Period	2/07/18 → 4/07/18

Keywords

Holistic AI
event board
knowledge representation
machine learning
conceptual spaces
attention mechanism

Access to Document

https://dblp.org/rec/conf/aic/GardenforsWJBVP18.html

Cite this

@inproceedings{1bb106c1961244f48973180c56b6c6d4,

title = "Event Boards as Tools for Holistic AI",

abstract = "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 {\textquoteleft}thematic roles{\textquoteright} 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.",

keywords = "Holistic AI, event board, knowledge representation, machine learning, conceptual spaces, attention mechanism",

author = "Peter G{\"a}rdenfors and Mary-Anne Williams and Benjamin Johnston and Richard Billingsley and Jonathan Vitale and Pavlos Peppas and Jesse Clark",

year = "2018",

language = "English",

pages = "1--10",

booktitle = "Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition",

publisher = "DBLP computer science bibliography",

note = "International Workshop on Artificial Intelligence and Cognition ; Conference date: 02-07-2018 Through 04-07-2018",

}

Gärdenfors, P, Williams, M-A, Johnston, B, Billingsley, R, Vitale, J, Peppas, P & Clark, J 2018, Event Boards as Tools for Holistic AI. in Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition. DBLP computer science bibliography, Italy, pp. 1-10, International Workshop on Artificial Intelligence and Cognition, Palermo, Italy, 2/07/18. <https://dblp.org/rec/conf/aic/GardenforsWJBVP18.html>

TY - GEN

T1 - Event Boards as Tools for Holistic AI

AU - Gärdenfors, Peter

AU - Williams, Mary-Anne

AU - Johnston, Benjamin

AU - Billingsley, Richard

AU - Vitale, Jonathan

AU - Peppas, Pavlos

AU - Clark, Jesse

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

KW - Holistic AI

KW - event board

KW - knowledge representation

KW - machine learning

KW - conceptual spaces

KW - attention mechanism

M3 - Conference proceeding contribution

SP - 1

EP - 10

BT - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition

PB - DBLP computer science bibliography

CY - Italy

T2 - International Workshop on Artificial Intelligence and Cognition

Y2 - 2 July 2018 through 4 July 2018

ER -

Event Boards as Tools for Holistic AI

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this