A HIGH-SPEED ARCHITECTURE FOR BUILDING HYBRID MINDS

Oisín Mac Fhearaí, Mark Humphrys, Ray Walshe

Abstract

A resurgence of interest has taken place supporting the idea of an intelligence composed of many simple components or "subminds". There is a growing consensus that, rather than a small number of "elegant" techniques for reasoning, inference or learning being the key to A.I., a model more likely to succeed would consist of perhaps thousands of simple agents co-operating such that an emergent intelligence is seen. The World-Wide Mind project is our attempt to facilitate this approach to scaling up artificial intelligence by enabling large hybrid systems to be built by multiple authors. The goal of the research described in this paper is to improve greatly the speed of the World-Wide Mind platform with a new communications protocol and implementation, to improve the user API and human interfaces, and to investigate methods of automatically constructing effective hybrid minds from the work of multiple authors, as well as to encourage collaboration between A.I. researchers worldwide.

References

  1. Asuncion, A. and Newman, D. (2009). UCI Machine Learning Repository. http://archive.ics.uci.edu/ml/.
  2. Brooks, R. A. (1991). Intelligence without representation.
  3. Bryson, J. J. (2007). Mechanisms of action selection: Introduction to the special issue. Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems, 15(1):5-8.
  4. Helsinger, A., Thome, M., and Wright, T. (2004). Cougaar: a scalable, distributed multi-agent architecture. In SMC, pages 1910-1917. IEEE.
  5. Humphrys, M. (2001). The world-wide-mind: Draft proposal.
  6. Kantrowitz, M. (2009). CMU Artificial Intelligence Repository. http://www.cs.cmu.edu/afs/cs/project/airepository/ai/0.html.
  7. Minsky, M. (1985). The Society of Mind. Simon and Schuster.
  8. Rogers, A., David, E., Jennings, N. R., and Schiff, J. (2007). The effects of proxy bidding and minimum bid increments within ebay auctions. TWEB, 1(2).
  9. Rouff, C. A. (2007). Introduction: Darpa urban grand challenge editorial). JACIC, 4(12):1046-1046.
  10. Sloman, A. (2002). How many separately evolved emotional beasties live within us?
  11. Sutton, R. S. and Barto, A. G. (1998). Reinforcement learning: An introduction. IEEE Transactions on Neural Networks, 9(5):1054-1054.
  12. Tyrrell, T. (1993). Computational Mechanisms for Action Selection. PhD thesis, University of Edinburgh.
  13. Visser, U. and Burkhard, H.-D. (2007). RoboCup: 10 years of achievements and future challenges. The AI Magazine, 28(2):115-132.
  14. Walshe, R., Humphrys, M., and O'Leary, C. (2004). Constructing complex brains: Building minds using subminds from biotechnology authors. In 1st IFIP Conference on Artificial Intelligence Applications and Innovations (AIAI-04), Toulouse, France, August 22-27, 2004, Proceedings.
Download


Paper Citation


in Harvard Style

Mac Fhearaí O., Humphrys M. and Walshe R. (2011). A HIGH-SPEED ARCHITECTURE FOR BUILDING HYBRID MINDS . In Proceedings of the 3rd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-40-9, pages 659-663. DOI: 10.5220/0003186906590663


in Bibtex Style

@conference{icaart11,
author={Oisín Mac Fhearaí and Mark Humphrys and Ray Walshe},
title={A HIGH-SPEED ARCHITECTURE FOR BUILDING HYBRID MINDS},
booktitle={Proceedings of the 3rd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2011},
pages={659-663},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003186906590663},
isbn={978-989-8425-40-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - A HIGH-SPEED ARCHITECTURE FOR BUILDING HYBRID MINDS
SN - 978-989-8425-40-9
AU - Mac Fhearaí O.
AU - Humphrys M.
AU - Walshe R.
PY - 2011
SP - 659
EP - 663
DO - 10.5220/0003186906590663