Skip to main content
SpringerLink
Log in

KWTA networks and their applications

  • Published:
Multidimensional Systems and Signal Processing Aims and scope Submit manuscript

Abstract

Winner-Take-All (WTA) or K-Winner-Take-All (KWTA) networks have been frequently used as the basic building blocks of complex neural networks. This paper introduces a new selection rule for network connections that implements stable KWTA networks. To widen the applications of WTA networks, a new class of WTA networks is proposed, and their efficient design methods are presented. We demonstrate the properties of the generalized class of WTA networks, through three application examples.

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, “A massively parallel architecture for a self-organizing neural pattern recognition machine,”Computer Visions, Graphics, and Image Processing, vol. 37, 1983, pp. 54–115.

    Google Scholar 

  2. G. A. Carpenter and S. Grossberg, “ART 2: Self-organization of stable category recognition codes for analog output patterns,”Applied Optics, vol. 26, 1987, pp. 4919–4930.

    Google Scholar 

  3. T. Kohonen,Self-Organization and Associative Memory, New York: Spring-Verlag, 1988.

    Google Scholar 

  4. R. P. Lippmann, B. Gold, and M. L. Malpass, “A comparison of Hamming and Hopfield nets for pattern classification,” Technical Report TR-769, Lincoln Laboratories, 1987.

  5. S. Y. Kung,Digital Neural Networks, Englewood Cliffs, NJ: PTR Prentice-Hall, Inc., 1993.

    Google Scholar 

  6. S. Grossberg, “Contour enhancement, short term memory, and constancies in reverberating neural networks,”Studies in Applied Mathematics, vol. LII (52), no. 3, 1973, pp. 213–257.

    Google Scholar 

  7. J. A. Feldman and D. H. Ballard, “Connectionist models and their properties,”Cognitive Science, vol. 6. 1982, pp. 205–254.

    Google Scholar 

  8. J. Lazzaro, S. Ryckebusch, M. A. Mahovald, and C. A. Mead, “Winner-take-all networks ofO (N) complexity,” inAdvances in Neural Information Processing Systems I, D. S. Touretzky, Ed., Palo Alto, CA: Morgan Kaufmann, pp. 703–711, 1989.

    Google Scholar 

  9. D. S. Touretzky, “Analyzing the energy landscapes of distributed winner-take-all networks,” inAdvances in Neural Information Processing Systems I, D. S. Touretzky, Ed., Palo Alto, CA: Morgan Kaufmann, pp. 626–633, 1989.

    Google Scholar 

  10. E. Majani, R. Erlanson, and Y. Abu-Mostafa, “On the k-winners-take-all network,” inAdvances in Neural Information Processing Systems I, D. S. Touretzky, Ed., Palo Alto, CA: Morgan Kaufmann, pp. 634–642, 1989.

    Google Scholar 

  11. W. J. Wolfe, D. Mathis, C. Anderson, J. Rothman, M. Gottler, G. Brady, R. Walker, G. Duane, and G. Alaghband, “K-winner network,”IEEE Trans. on Neural Networks, vol. 2, 1991, pp. 310–315.

    Google Scholar 

  12. R. Erlanson and Y. Abu-Mostafa, “Analog neural networks as decoders,” inAdvances in Neural Information Processing Systems I, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds., San Mateo, CA: Morgan Kaufmann, pp. 585–588, 1991.

    Google Scholar 

  13. J. J. Hopfield, “Neurons with graded response have collective computational properties like those of two-state neurons,”Proc. Natl. Acad. Sci. USA, vol. 81, 1984, pp. 3088–3092.

    Google Scholar 

  14. J. J. Hopfield and D. W. Tank, “‘Neural’ computation of decision in optimization problems,”Biol. Cybern., vol. 52, 1985, pp. 141–152.

    Google Scholar 

  15. R. S. Francis, and I. D. Mathieson, “Benchmark parallel sort for shared memory multiprocessors,”IEEE Tans. on Computers, vol. C-37, 1988, pp. 1619–1626.

    Google Scholar 

  16. P. Shi and R. K. Ward, “OSNet: A Neural Network Implementation of Order Statistic Filters,”IEEE Trans. on Neural Networks, vol. 4, 1993, pp. 234–241.

    Google Scholar 

  17. A. C. Bovic, T. S. Huang, and D. C. Muson, “A generalization of median filtering using combinations of order statistics,”IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. ASSP-31, 1983, pp. 1342–1350.

    Google Scholar 

  18. I. Pitas and A. N. Venetsanopoulos, “Edge detectors based on nonlinear filters,”Signal Processing, vol. 10, 1986, pp. 395–413.

    Google Scholar 

  19. B. Johnson,Design and Analysis of Fault Tolerant Digital Systems, Reading, MA: Addison-Wesley, 1989.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, University of Minnesota, Duluth, 271 MWAH, 10 University Dr., 55812, Duluth, MN

    Taek Mu Kwon & Michael Zervakis

Authors
  1. Taek Mu Kwon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Zervakis
    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

Kwon, T.M., Zervakis, M. KWTA networks and their applications. Multidim Syst Sign Process 6, 333–346 (1995). https://doi.org/10.1007/BF00983559

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00983559

Keywords

Search

Navigation