Measuring Self-Organization via Observers

  • Daniel Polani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2801)


We introduce organization information, an information-theoretic characterization for the phenomenon of self-organization. This notion, which requires the specification of an observer, is discussed in the paradigmatic context of the Self-Organizing Map and its behaviour is compared to that of other information-theoretic measures. We show that it is sensitive to the presence and absence of “self-organization” (in the intuitive sense) in cases where conventional measures fail.


Information Gain Random State Organization Information State Probability Distribution Intrinsic Information 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Adami, C.: Introduction to Artificial Life. Springer, Heidelberg (1998)zbMATHGoogle Scholar
  2. 2.
    Ashby, W.R.: Principles of the self-organizing dynamic system. J. Gen. Psychol. 37, 125–128 (1947)CrossRefGoogle Scholar
  3. 3.
    Baas, N.A., Emmeche, C.: On Emergence and Explanation. Intellectica 2(25), 67–83 (1997)Google Scholar
  4. 4.
    Crutchfield, J.P.: The Calculi of Emergence: Computation, Dynamics, and Induction. Physica D, 11–54 (1994)Google Scholar
  5. 5.
    Erwin, E., Obermayer, K., Schulten, K.: Self-Organizing Maps: ordering,convergence properties and energy functions. Biol. Cybern. 67, 47–55 (1992)zbMATHCrossRefGoogle Scholar
  6. 6.
    Goodhill, G.J., Sejnowski, T.J.: A unifying objective function for topographic mappings. Neural Computation 9, 1291–1304 (1997)CrossRefGoogle Scholar
  7. 7.
    Haken, H.: Advanced synergetics. Springer, Berlin (1983)zbMATHGoogle Scholar
  8. 8.
    Harvey, I.: The 3 Es of Artificial Life: Emergence, Embodiment and Evolution. Invited talk at Artificial Life VII, 1–6. August, Portland (2000)Google Scholar
  9. 9.
    Heylighen, F., Joslyn, C., Turchin, V.: Principia Cybernetica Web (March 2003),
  10. 10.
    Jetschke, G.: 1 Mathematik der Selbstorganisation. Vieweg, Braunschweig (1989)Google Scholar
  11. 11.
    Kohonen, T.: Self-Organization and Associative Memory, 3rd edn. Springer Series in Information Sciences, vol. 8. Springer, Heidelberg (1989)Google Scholar
  12. 12.
    Kohonen, T.: Self-Organizing Maps, 2nd edn. Springer, Heidelberg (1997)zbMATHGoogle Scholar
  13. 13.
    Kushner, H.J., Clark, D.S.: Stochastic Approximation for Constrained and Unconstrained Systems. Applied Math. Science Series, vol. 26. Springer, Heidelberg (1978)Google Scholar
  14. 14.
    Pask, G.: The Natural History of Networks. In: [26] (1960)Google Scholar
  15. 15.
    Polani, D.: Measures for the Organization of Self-Organizing Maps. In: Jain, L., Seiffert, U. (eds.) Self-Organizing Neural Networks. Recent Advances and Applications. Springer, Heidelberg (2001)Google Scholar
  16. 16.
    Polani, D.: On Individuality, Emergence and Information Preservation. In: Nehaniv, C.L., te Boekhorst, R. (eds.) Proceedings of the Symposium on Evolvability and Individuality, September 18–20, 2002. St. Albans. University of Hertfordshire (2002)Google Scholar
  17. 17.
    Prigogine, I., Nicolis, G.: Self-Organization in Non-Equilibrium Systems: From Dissipative Structures to Order Through Fluctuations. J. Wiley & Sons, New York (1977)Google Scholar
  18. 18.
    Rasmussen, S., Baas, N., Mayer, B., Nilsson, M., Olesen, M.W.: Ansatz for Dynamical Hierarchies. Artificial Life 7, 329–353 (2001)CrossRefGoogle Scholar
  19. 19.
    Reichl, L.: A Modern Course in Statistical Physics. University of Texas Press, Austin (1980)Google Scholar
  20. 20.
    Ritter, H., Martinetz, T., Schulten, K.: Neuronale Netze. Addison-Wesley, Reading (1994)Google Scholar
  21. 21.
    Shalizi, C.R.: Is the Primordial Soup Done Yet?, January 23 (2001) (1996),–organization/soup–done/
  22. 22.
    Spitzner, A., Polani, D.: Order Parameters for Self-Organizing Maps. In: Niklasson, L., Bodén, M., Ziemke, T. (eds.) Proc. of the 8th Int. Conf. on Artificial Neural Networks (ICANN 1998), Skövde, Sweden, vol. 2, pp. 517–522. Springer, Heidelberg (1998)Google Scholar
  23. 23.
    Tononi, G., Sporns, O., Edelman, G.M.: A measure for brain complexity: Relating functional segregation and integration in the nervous system. Proc. Natl. Acad. Sci. USA 91, 5033–5037 (1994)CrossRefGoogle Scholar
  24. 24.
    Villmann, T., Der, R., Herrmann, M., Martinetz, T.: Topology Preservation in Self-Organizing Feature Maps: Exact Definition and Measurement. IEEE Trans. Neural Networks 8(2), 256–266 (1997)CrossRefGoogle Scholar
  25. 25.
    Walter, W.G.: A Machine that Learns. Scientific American, 60–63 (1951)Google Scholar
  26. 26.
    Yovits, M.C., Cameron, S. (eds.): Self-Organizing Systems. In: Proceedings of an Interdisciplinary Conference, May 5–6, 1959. Computer Science and Technology and their Application. Pergamon Press, Oxford (1960)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Daniel Polani
    • 1
  1. 1.Adaptive Systems Research Group, Department of Computer ScienceUniversity of Hertfordshire 

Personalised recommendations