Abstract
Many existing AGI architectures are based on the assumption of infinite computational resources, as researchers ignore the fact that real-world tasks have time limits, and managing these is a key part of the role of intelligence. In the domain of intelligent systems the management of system resources is typically called “attention”. Attention mechanisms are necessary because all moderately complex environments are likely to be the source of vastly more information than could be processed in realtime by an intelligence’s available cognitive resources. Even if sufficient resources were available, attention could help make better use of them. We argue that attentional mechanisms are not only nice to have, for AGI architectures they are an absolute necessity. We examine ideas and concepts from cognitive psychology for creating intelligent resource management mechanisms and how these can be applied to engineered systems. We present a design for a general attention mechanism intended for implementation in AGI architectures.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baars, B.J., Franklin, S.: Consciousness is computational: The LIDA model of Global Workspace Theory. Intl. Journal of Machine Consciousness 1(1), 23–32 (2009)
Broadbent, D.E.: Perception and Communication. Pergamon, London (1958)
Cherry, E.C.: Some experiments on the recognition of speech, with one and two ears. Journal of the Acoustical Society of America, 975–979 (1953)
Nivel, E.: Ikon Flux 2.0. Reykjavik University technical report (2007), http://www.ru.is/media/skjol-td/RUTR-CS07006.pdf
Nivel, E., Thórisson, K.R.: Self-Programming: Operationalizing Autonomy. In: Proceedings of the 2nd Conf. on Artificial General Intelligence (2008)
Norman, D.A.: Memory while shadowing. Quarterly Journal of Experimental Psychology 21, 85–93 (1969)
Schmidhuber, J., Huber, R.: Learning to generate artificial fovea trajectories for target detection. International Journal of Neural Systems 2(1&2), 135–141 (1991)
Skubic, M., Noelle, D., Wilkes, M., Kawamura, K., Keller, J.M.: A biologically inspired adaptive working memory for robots. In: AAAI Fall Symp., Workshop on the Intersection of Cognitive Science and Robotics, Washington, D.C. (2004)
Sun, R.: The CLARION cognitive architecture: Extending cognitive modelling to social simulation. In: Sun, R. (ed.) Cognition and Multi-Agent Interaction. Cambridge University Press, New York (2006)
Thórisson, K.R., Nivel, E.: Achieving artificial general intelligence through peewee granularity. In: Proc. of the 2nd Conf. on Artificial General Intelligence, pp. 220–221 (2009a)
Thórisson, K.R., Nivel, E.: Holistic intelligence: Transversal skills and current methodologies. In: Proc. of the 2nd Conf. on Artificial General Intelligence, pp. 222–223 (2009b)
Thórisson, K.R.: From Constructionist to Constructivist A.I. Keynote, Technical Report, FS-90-01. AAAI Press, Menlo Park, California (2009c)
Thórisson, K.R., Helgason, H.P.: Cognitive Architectures and Autonomy: A Comparative review. Journal of Artificial General Intelligence 3, 1–30 (2012)
Wang, P.: Non-Axiomatic Reasoning System: Exploring the Essence of Intelligence. Ph.D. diss., Dept. of Computer Science, Indiana Univ., CITY, Indiana (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Helgason, H.P., Nivel, E., Thórisson, K.R. (2012). On Attention Mechanisms for AGI Architectures:A Design Proposal. In: Bach, J., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2012. Lecture Notes in Computer Science(), vol 7716. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35506-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-35506-6_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35505-9
Online ISBN: 978-3-642-35506-6
eBook Packages: Computer ScienceComputer Science (R0)