Attention Capabilities for AI Systems

Helgi Páll Helgason, Kristinn R. Thórisson

Abstract

Much of present AI research is based on the assumption of computational systems with infinite resources, an assumption that is either explicitly stated or implicit in the work as researchers ignore the fact that most real-world tasks must be finished within certain time limits, and it is the role of intelligence to effectively deal with such limitations. Expecting AI systems to give equal treatment to every piece of data they encounter is not appropriate in most real-world cases; available resources are likely to be insufficient for keeping up with available data in even moderately complex environments. Even if sufficient resources are available, they might possibly be put to better use than blindly applying them to every possible piece of data. Finding inspiration for more intelligent resource management schemes is not hard, we need to look no further than ourselves. This paper explores what human attention has to offer in terms of ideas and concepts for implementing intelligent resource management and how the resulting principles can be extended to levels beyond human attention. We also discuss some ideas for the principles behind attention mechanisms for artificial (general) intelligences.

References

  1. Baars, B. J., Franklin, S. 2009. Consciousness is computational: The LIDA model of Global Workspace Theory. International Journal of Machine Consciousness, 2009, 1(1): p. 23-32.
  2. Broadbent, D. E. 1958. Perception and Communication. London: Pergamon.
  3. Cherry, E. C. 1953. Some experiments on the recognition of speech, with one and two ears. Journal of the Acoustical Society of America. Pages 975-979.
  4. Knudsen, E. I. 2007. Fundamental components of attention. Annu Rev Neurosci, volume 30. Pages 57-78.
  5. James, W. 1890. The Principles of Psychology. New York: Henry Holt, Vol.1, pages 403-404.
  6. Norman, D. A. 1969. Memory while shadowing. Quarterly Journal of Experimental Psychology, vol. 21, pages 85-93.
  7. Novianto, R., Williams, M.-A. 2009. The Role of Attention in Robot Self-Awareness, The 18th International Symposium on Robot and Human Interactive Communication. Pages 1047-1053.
  8. Laird, J. E. 2008. Extending the SOAR cognitive architecture. In Proceedings of the artificial general intelligence conference. Memphis. TN: IOS Press.
  9. Phillips, J. L. 2005. A biologically inspired working memory framework for robots. Proc. 27th Ann. Conf. Congitive Science Society. Pages 1750-1755.
  10. Skubic, M., Noelle, D., Wilkes, M., Kawamura, K., Keller, J.M. 2004. A biologically inspired adaptive working memory for robots. AAAI Fall Symp., Workshop on the Intersection of Cognitive Science and Robotics. Washington D.C. 2004.
  11. Sun, R. 2006. The CLARION cognitive architecture: Extending cognitive modelling to social simulation. In: Ron Sun (ed.), Cognition and Multi-Agent Interaction. Cambridge University Press, New York.
  12. Thórisson, K. R. 2009. From Constructionist to Constructivist A. I. Keynote, Technical Report, FS-90- 01, AAAI press, Menlo Park, California.
  13. Wang, P. 1995. Non-Axiomatic Reasoning System: Exploring the Essence of Intelligence. Ph.D. diss., Dept. of Computer Science, Indiana Univ., CITY, Indiana.
Download


Paper Citation


in Harvard Style

Páll Helgason H. and R. Thórisson K. (2012). Attention Capabilities for AI Systems . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8565-21-1, pages 281-286. DOI: 10.5220/0004120502810286


in Bibtex Style

@conference{icinco12,
author={Helgi Páll Helgason and Kristinn R. Thórisson},
title={Attention Capabilities for AI Systems},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2012},
pages={281-286},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004120502810286},
isbn={978-989-8565-21-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Attention Capabilities for AI Systems
SN - 978-989-8565-21-1
AU - Páll Helgason H.
AU - R. Thórisson K.
PY - 2012
SP - 281
EP - 286
DO - 10.5220/0004120502810286