Advertisement

A fractal, selforganizing map with partially chaotic neurons

  • A. Kosak
  • K. Goser
Organization Principles
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)

Abstract

A new type of a chaotic neuron is proposed which allows a new, simplified architecture of selforganizing maps. The chaotic neurons are examined with respect to their application in selforganizing maps. A new concept of self-organizing maps with fractal architecture is proposed and its suitability for a VLSI-implementation is examined. It is shown that the efficiency of conventional selforganizing maps can be overcome while the expenditure, with regard to a hardware-realisation, is notably reduced.

Keywords

Input Vector Chaotic Behaviour Level Module Iteration Function Hardware Realization 
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]
    Kohonen, T.: Automatic Formation of Topological Maps of Patterns in a Selforganizing System, Proceedings of the 2nd Scandinavian Conference on Image Analysis, Helsinki (June 15–17, 1981), pp. 1–7.Google Scholar
  2. [2]
    Kohonen, T.: Self-Organised Formation of Topology Correct Feature Maps, Biological Cybernetics 43 (1982), pp. 59–69.Google Scholar
  3. [3]
    Dingle, Allison A., Andreae, John H., Jones, Richard D.: A Chaotic Neural Unit, IEEE 5/93, 1993, pp 335–340.Google Scholar
  4. [4]
    Tryba, Viktor: Selbstorganisierende Karten: Theorie, Anwendung und VLSI-Implementierung, Fortschrittsberichte VDI, Reihe 9: Elektronik, Nr. 151.Google Scholar
  5. [5]
    Jaggard, Dwight, L.: Special Section on Fractals in Electrical Engineering, Proceedings of the IEEE, Vol. 81, No. 10, October 1993, pp 1423–1427.Google Scholar
  6. [6]
    S. Rüping, U. Rückert, K. Goser: Hardware design for a Self-Organizing Feature Map with binary Input Vectors, Proceedings for IWANN (1993), Sitges (Spain), pp 488–493.Google Scholar
  7. [7]
    R.W. Leven, B.-P. Koch, B. Pompe: Chaos in dissipativen Systemen, Vieweg1989, pp 13, 53, 102Google Scholar
  8. [8]
    Eryk Infeld, George Rowlands: Nonlinear waves, solitons and chaos, Cambridge University Press, 1990Google Scholar
  9. [9]
    James Testa, José Pérez, Carson Jeffries: Evidence for Universal Chaotic Behaviour of a Driven Nonlinear Oszillator, Physical Review Letters, 1982, Volume 48, pp 714–717Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • A. Kosak
    • 1
  • K. Goser
    • 1
  1. 1.Faculty of Electrical EngineeringUniversity of DortmundDortmundGermany

Personalised recommendations