Advertisement

Making Sense of the Sensory Data – Coordinate Systems by Hierarchical Decomposition

  • Attila Egri-Nagy
  • Chrystopher L. Nehaniv
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4253)

Abstract

Having the right sensory channels is an important ingredient for building an autonomous agent, but we still have the problem of making sense of the sensory data for the agent. This is the basic problem of artificial intelligence. Here we propose an algebraic method for generating abstract coordinate system representations of the environment based on the agent’s actions. These internal representations can be refined and regenerated during the lifespan of the agent.

Keywords

Sensory Data Hide State Wreath Product Prime Decomposition State Automaton 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brooks, R.A.: Cambrian Intelligence: The Early History of the New AI. MIT Press (A Bradford Book), Cambridge (1999)MATHGoogle Scholar
  2. 2.
    Steels, L.: Intelligence with representation. Philosophical Transactions: Mathematical, Physical and Engineering Sciences 361(1811), 2381–2395 (2003)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Rhodes, J.L.: Applications of Automata Theory and Algebra via the Mathematical Theory of Complexity to Finite-State Physics, Biology, Philosophy, Games, and Codes. University of California at Berkeley, Mathematics Library (1971)Google Scholar
  4. 4.
    Nehaniv, C.L., Rhodes, J.L.: The evolution and understanding of hierarchical complexity in biology from an algebraic perspective. Artificial Life 6, 45–67 (2000)CrossRefGoogle Scholar
  5. 5.
    Devadas, S., Newton, A.R.: Decomposition and factorization of sequential finite state machinces. IEEE Transactions on Computer-Aided Design 8(11), 1206–1217 (1989)CrossRefGoogle Scholar
  6. 6.
    Egri-Nagy, A., Nehaniv, C.L.: Algebraic hierarchical decomposition of finite state automata: Comparison of implementations for krohn-rhodes theory. In: Domaratzki, M., Okhotin, A., Salomaa, K., Yu, S. (eds.) CIAA 2004. LNCS, vol. 3317, pp. 315–316. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Egri-Nagy, A., Nehaniv, C.L.: GrasperMachine, Computational Semigroup Theory for Formal Models of Understanding (2003), http://graspermachine.sf.net
  8. 8.
    Egri-Nagy, A.: Algebraic Hierarchical Decomposition of Finite State Automata – A Computational Approach. PhD thesis, University of Hertfordshire, School of Computer Science (2005)Google Scholar
  9. 9.
    Krohn, K., Rhodes, J.L., Tilson, B.R.: 5, The Prime Decomposition Theorem of the Algebraic Theory of Machines. In: Arbib, M.A. (ed.) Algebraic Theory of Machines, Languages, and Semigroups, pp. 81–125. Academic Press, London (1968)Google Scholar
  10. 10.
    von Uexküll, J.: Environment [Umwelt] and inner world of animals. In: Burghardt, G.M. (ed.) Foundations of Comparative Ethology, Van Nostrand Reinhold, New York, pp. 222–245 (1985)Google Scholar
  11. 11.
    Klyubin, A.S., Polani, D., Nehaniv, C.L.: Organization of the information flow in the perception-action loop of evolved agents. In: Zebulum, R.S., Gwaltney, D., Hornby, G., Keymeulen, D., Lohn, J., Stoica, A. (eds.) Proceedings of 2004 NASA/DoD Conference on Evolvable Hardware, pp. 177–180. IEEE Computer Society, Los Alamitos (2004)CrossRefGoogle Scholar
  12. 12.
    Crutchfield, J.P.: The calculi of emergence: Computation, dynamics, and induction. Physica D 75, 11–54 (1994)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Attila Egri-Nagy
    • 1
  • Chrystopher L. Nehaniv
    • 1
  1. 1.BioComputation Research Group, School of Computer ScienceUniversity of HertfordshireHertfordshireUnited Kingdom

Personalised recommendations