A role for consciousness in action selection

Research output: Contribution to conferencePaper

  • 3 Citations

Abstract

This paper argues that conscious attention exists not so much for selecting an immediate action as for focusing learning of the action-selection mechanisms and predictive models on tasks and environmental contingencies likely to affect the conscious agent. It is perfectly possible to build this sort of system into machine intelligence, but it is not strictly necessary unless the intelligence needs to learn and is resource-bounded with respect to the rate of learning vs. the rate of relevant environmental change. Support of this theory is drawn from scientific research and AI simulations, and a few consequences are suggested with respect to self consciousness and ethical obligations to and for AI.

Conference

ConferenceProceedings of the AISB 2011 Symposium: Machine Consciousness
CountryUK United Kingdom
CityUniversity of York
Period6/04/117/04/11

Fingerprint

learning
environmental change
resource
simulation
rate
scientific research

Cite this

Bryson, J. J. (2011). A role for consciousness in action selection. 15-20. Paper presented at Proceedings of the AISB 2011 Symposium: Machine Consciousness, University of York, UK United Kingdom.

A role for consciousness in action selection. / Bryson, Joanna J.

2011. 15-20 Paper presented at Proceedings of the AISB 2011 Symposium: Machine Consciousness, University of York, UK United Kingdom.

Research output: Contribution to conferencePaper

Bryson, JJ 2011, 'A role for consciousness in action selection' Paper presented at Proceedings of the AISB 2011 Symposium: Machine Consciousness, University of York, UK United Kingdom, 6/04/11 - 7/04/11, pp. 15-20.
Bryson JJ. A role for consciousness in action selection. 2011. Paper presented at Proceedings of the AISB 2011 Symposium: Machine Consciousness, University of York, UK United Kingdom.
Bryson, Joanna J. / A role for consciousness in action selection. Paper presented at Proceedings of the AISB 2011 Symposium: Machine Consciousness, University of York, UK United Kingdom.6 p.
@conference{9e624c914c76426ab54dbb3b5cf31eb6,
title = "A role for consciousness in action selection",
abstract = "This paper argues that conscious attention exists not so much for selecting an immediate action as for focusing learning of the action-selection mechanisms and predictive models on tasks and environmental contingencies likely to affect the conscious agent. It is perfectly possible to build this sort of system into machine intelligence, but it is not strictly necessary unless the intelligence needs to learn and is resource-bounded with respect to the rate of learning vs. the rate of relevant environmental change. Support of this theory is drawn from scientific research and AI simulations, and a few consequences are suggested with respect to self consciousness and ethical obligations to and for AI.",
author = "Bryson, {Joanna J}",
year = "2011",
month = "4",
language = "English",
pages = "15--20",
note = "Proceedings of the AISB 2011 Symposium: Machine Consciousness ; Conference date: 06-04-2011 Through 07-04-2011",

}

TY - CONF

T1 - A role for consciousness in action selection

AU - Bryson,Joanna J

PY - 2011/4

Y1 - 2011/4

N2 - This paper argues that conscious attention exists not so much for selecting an immediate action as for focusing learning of the action-selection mechanisms and predictive models on tasks and environmental contingencies likely to affect the conscious agent. It is perfectly possible to build this sort of system into machine intelligence, but it is not strictly necessary unless the intelligence needs to learn and is resource-bounded with respect to the rate of learning vs. the rate of relevant environmental change. Support of this theory is drawn from scientific research and AI simulations, and a few consequences are suggested with respect to self consciousness and ethical obligations to and for AI.

AB - This paper argues that conscious attention exists not so much for selecting an immediate action as for focusing learning of the action-selection mechanisms and predictive models on tasks and environmental contingencies likely to affect the conscious agent. It is perfectly possible to build this sort of system into machine intelligence, but it is not strictly necessary unless the intelligence needs to learn and is resource-bounded with respect to the rate of learning vs. the rate of relevant environmental change. Support of this theory is drawn from scientific research and AI simulations, and a few consequences are suggested with respect to self consciousness and ethical obligations to and for AI.

M3 - Paper

SP - 15

EP - 20

ER -