Skip to main content
SpringerLink
Log in

Optimal Algorithmic Complexity of Fuzzy ART

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

We discuss implementations of the Adaptive Resonance Theory (ART) on a serial machine. The standard formulation of ART, which was inspired by recurrent brain structures, corresponds to a recursive algorithm. This induces an algorithmic complexity of order O(N2)+O(MN) in worst and average case, N being the number of categories, and M the input dimension. It is possible, however, to formulate ART in a non-recursive algorithm such that the complexity is of order O(MN) only.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. G.A. Carpenter and S. Grossberg, Pattern Recognition by Self-Organizing Neural Networks, Cambridge, MA: MIT Press, 1991; G.A. Carpenter, S. Grossberg, and D.B. Rosen, “Fuzzy ART: An adaptive resonance algorithm for rapid, stable classification of analog patterns”, in Proc. Int. Joint Conf. Neural Networks, Vol. II, pp. 411–420; G.A. Carpenter, S. Grossberg, and D.B. Rosen, “Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system”, Neural Networks, Vol. 4, pp. 759–771, 1991.

    Google Scholar 

  2. D.J. Felleman and D.C. Van Essen, “Distributed hierarchical processing in primate visual cortex”, Cerebral Cortex Vol. 1, pp. 1–47, 1991.

    Google Scholar 

  3. R. Douglas, C. Koch. M. Mahowald, K. Martin, H. Suarez, “Recurrent excitation in neocortical circuits”, Science, 269, pp. 981–985, 1995.

    Google Scholar 

  4. T. Deacon, “Holism and associationism in neuropsychology: an anatomical synthesis”, in E. Perecman (ed.), Integrating theory and practice in clinical neuropsychology, Erlbaum, Hillsdale NJ, 1988.

    Google Scholar 

  5. E.T. Rolls, “The representation of information in the temporal lobe visual cortical areas of macaques”, in R. Eckmiller (ed.), Advanced Neural Computers, Elsevier, New York, pp. 69–78, 1990.

    Google Scholar 

  6. D. Mumford, “On the computational architecture of the neocortex: II. The role of the corticocortical loops”, Biolog. Cybern. Vol. 66, pp. 241–251, 1992.

    Google Scholar 

  7. P.N. Rajesh Rao and D.H. Ballard, “Dynamicmodel of visual recognition predicts neural response properties in the visual cortex”, (to appear in Neural Computation) Technical report Rochester Univ., 96.2 (revision of TR 95.4), 1996.

  8. S. Grossberg, “The attentive brain”, American Scientist, 83, pp. 438–449, 1995.

    Google Scholar 

  9. A.V. Aho, J.E. Hopcroft, and J.D. Ullman, Data Structures and Algorithms, Addison-Wesley, 1988; R. Sedgewick, Algorithms in C++, Addison-Wesley, 1988.

Download references

Author information

Authors and Affiliations

  1. Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780, Bochum, Germany

    T. Burwick & F. Joublin

Authors
  1. T. Burwick
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. F. Joublin
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Burwick, T., Joublin, F. Optimal Algorithmic Complexity of Fuzzy ART. Neural Processing Letters 7, 37–41 (1998). https://doi.org/10.1023/A:1009632604848

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1009632604848

Search

Navigation