ICANN ’93 pp 59-62 | Cite as

Improving Categorization with CALM Maps

  • Ed Lebert
  • R. Hans Phaf
Conference paper

Abstract

The Categorizing And Learning Module (CALM) represents different patterns on different nodes through a competitive learning procedure. We study an extension of CALM that enforces a topological structure on the representations. The main difference with Kohonen’s self-organizing feature map is that no external regulating mechanisms are needed to learn a stable map. Simulations show that this CALM Map, in comparison to the standard CALM module, improves categorization because the stretching property of CALM Maps enables a continuous process of separation, whereas CALM will eventually commit itself to a once obtained categorization.

Keywords

Topo Erwin Hemel 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    E. Erwin, K. Obermayer, and K. Schulten. Self-organizing maps: Stationary states, metastability and convergence rate. Biological Cybernetics, 67: 47–55, 1992.CrossRefMATHGoogle Scholar
  2. [2]
    C.D. Gilbert and T.N. Wiesel. Columnar specificity of intrinsic horizontal and corticocortical connections in cat visual cortex. The Journal of Neuroscience, 9: 2432–2442, 1989.Google Scholar
  3. [3]
    T. Kohonen. Self-organization and associative memory. Springer-Verlag, Berlin, 2nd edition, 1988.CrossRefMATHGoogle Scholar
  4. [4]
    J.M.J. Murre. Learning and categorization in modular neural networks. Harvester Wheatsheaf, Hemel Hempstead, U.K., 1992.Google Scholar
  5. [5]
    J.M.J. Murre, R.H. Phaf, and G. Wolters. CALM: Categorizing and learning module. Neural Networks, 5: 55–82, 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • Ed Lebert
    • 1
  • R. Hans Phaf
    • 1
  1. 1.Psychonomics DepartmentUniversity of AmsterdamAmsterdamThe Netherlands

Personalised recommendations