Advertisement

Self-Organizing Maps for Representing Structures

  • Igor Farkaš
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 5)

Abstract

We propose a novel neural network model for representing data structures. The model consists of a hierarchy of Self-Organizing Maps (SOMs) equipped with leaky integrating units. Each of the maps is thus designed to represent sequences of data in a fashion resembling Barnsley’s iterated function system. Each data structure is decomposed into a hierarchy of sequences where in all but the lowest levels a special symbol is substituted to represent corresponding subtrees. The advantage of this representation is that it is directly computable, and if neurally implemented using SOMs, it is computationally unexpensive. Preliminary simulations using simple symbolic tree structures demonstrate that obtained representations have the required property of systematic order.

Keywords

Iterate Function System Symbolic Sequence Input Alphabet Leaky Integrator ofIFS Sequence 
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.
    J.A. Fodor and Z.W. Pylyshyn. Connectionism and cognitive architecture: A critical analysis. Cognition, 28: 3–71, 1988.CrossRefGoogle Scholar
  2. 2.
    J.B. Pollack. Recursive distributed representations. Artificial Intelligence, 46 (12): 77–105, 1990.CrossRefGoogle Scholar
  3. 3.
    P. Smolensky. Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artif. Intelligence, 46: 159–216, 1990.MathSciNetMATHCrossRefGoogle Scholar
  4. 4.
    T. Plate. Holographic reduced representations. IEEE Transactions on Neural Networks6(3):623–641, 1995 Google Scholar
  5. 5.
    L. Shastri and V. Ajjanagadde. From simple associations to systematic reasoning. Behavioral nad Brain Sciences, 16 (3): 417–494, 1993.CrossRefGoogle Scholar
  6. 6.
    J.E. Hummel and K.J. Holyoak. Distributed representations of structure: a theory of analogical access and mapping. Psych. Review, 104 (3): 427–466, 1997.CrossRefGoogle Scholar
  7. 7.
    D.J. James and R. Miikkulainen. Sardnet: a self-organizing feature map for sequences. In Advances in Neural Information Processing Systems 7, 1995.Google Scholar
  8. 8.
    K. Kopecz. Unsupervised learning of sequences on maps with lateral connectivity. In ICANN’95, pages 431–436, Paris, France, 1995.Google Scholar
  9. 9.
    J. Göppert and W. Rosenstiel. Dynamic extensions of self-organizing maps. InProceedings of ICANN’94pages 330–333, 1994 Google Scholar
  10. 10.
    G.J. Chappell and J.G. Taylor. The temporal Kohonen map.Neural Networks6:441–445, 1993 Google Scholar
  11. 11.
    T. Koskela et al. Time series prediction using recurrent SOM with local linear models. Int. Journal of Knowledge-Based Intell. Eng. Systems, 2: 60–68, 1998.Google Scholar
  12. 12.
    M. Barnsley. Fractals Everywhere. Academic Press, 1988 Google Scholar
  13. 13.
    I. Farkas. Invariance of gaussian-vector mapping using a self-organizing map.Neural Network World7(2):153–159, 1997 Google Scholar
  14. 14.
    L. Niklasson and M. Bodén. Representing structure and structured representations in connectionist networks. In A. Browne, editor, Neural Network Perspectives on Cognition and Adaptive Robotics, pages 20–50. IOP Press, 1997.Google Scholar
  15. 15.
    P. Tino. Spatial representation of symbolic sequences through iterated function systems. IEEE Trans. on Systems, Man and Cybernetics, 29 (4): 386–392, 1999.Google Scholar
  16. 16.
    T. Kohonen. Self-organizing maps of symbol strings. Technical report A42Helsinki University of Technology, Espoo, Finland, 1996 Google Scholar
  17. 17.
    N.E. Sharkey Connectionist representation techniques.Artificial Intelligence Review5:143–167, 1990 Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Igor Farkaš
    • 1
  1. 1.Institute of Measurement ScienceSlovak Academy of SciencesBratislavaSlovak Republic

Personalised recommendations