Advertisement

Individual evolutionary algorithm and its application to learning of nearest neighbor based MLP

  • Qiangfu Zhao
  • Tatsuo Higuchi
Learning
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)

Abstract

A society S(I, T) is defined as a system consisting of an individual set I and a task set T. This paper studies the problem to find an efficient S such that all tasks in T can be fulfilled using the smallest I. The individual evolutionary algorithm (IEA) is proposed to solve this problem. By IEA, each individual finds and adapts itself to a class of tasks through evolution, and an efficient S can be obtained automatically. The IEA consists of four operations: competition, gain, loss and retraining. Competition tests the performance of the recent I and the fitness of each individual; gain increases the performance of I by adding new individuals; loss makes I more compact by removing individuals with very low fitness; and individuals are adjusted by retraining to make them better. An evolution cycle is: competition ∨ (gainloss) ∧ retraining, and the evolution is performed cycle after cycle until some criterion is satisfied. The performance of IEA is verified by applying it to the learning of nearest neighbor based multilayer perceptrons.

Keywords

Evolutionary algorithm genetic algorithm individual evolutionary algorithm multi-individual-multi-task problem nearest neighbor based multilayer perceptron 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    X. Yao, “Evolutionary artificial neural networks,” International Journal of Neural Systems, Vol. 4, No. 3, 203–222, Sept. 1993.PubMedGoogle Scholar
  2. [2]
    D. B. Fogel, “An introduction to simulated evolutionary optimization,” IEEE Trans. on Neural Networks, Vol. 5, No. 1, pp. 3–14, Jan. 1994.Google Scholar
  3. [3]
    T. M. Cover and P. E. Hart, “Nearest neighbor pattern classification,” IEEE Trans. on Information Theory, Vol. IT-13, No. 1, pp. 21–27, Jan. 1967.Google Scholar
  4. [4]
    Q. F. Zhao and T. Higuchi, “A study on the determination of MLP structures,” Proc. IEICE Karuizawa Workshop, pp. 121–126, Karuizawa, Japan, April 1994.Google Scholar
  5. [5]
    Q. F. Zhao, “Neural network realization of the nearest neighbor methods,” Technical Report of IEICE, NC93-65, pp. 83–87, Dec. 1993.Google Scholar
  6. [6]
    Q. F. Zhao and T. Higuchi, “Efficient learning of nearest neighbor multilayer perceptrons.” Proc. International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pp. 77–78, Iizuka, Japan, Aug. 1994.Google Scholar
  7. [7]
    Q. F. Zhao and T. Higuchi, “Supervised organization of nearest neighbor MLP,” Proc. International Conference on Neural Information Processing, pp. 1398–1403, Seoul, Korea, Oct. 1994.Google Scholar
  8. [8]
    O. J. Murphy, “Nearest neighbor pattern classification perceptrons,” Proc. IEEE, Vol. 78, No. 10, pp. 1595–1598, Oct. 1990.Google Scholar
  9. [9]
    N. K. Bose and A. K. Garga, “Neural network design using Voronoi diagrams,” IEEE Trans. on Neural Networks, Vol. 4, No. 5, pp. 778–787, Sept. 1993.Google Scholar
  10. [10]
    T. Kohonen, “Self-organized formation of topologically correct feature maps,” Biolog. Cybern., Vol. 43, pp. 59–69, 1982.Google Scholar
  11. [11]
    T. Kohonen, “The self-organizing map,” Proc. IEEE, Vol. 78, No. 9, pp. 1464–1480, Sept. 1990.Google Scholar
  12. [12]
    J. A. Kangas, T. Kohonen and J. T. Laaksonen, “Variants of self-organizing maps,” IEEE Trans. on Neural Networks, Vol. 1, No. 1, pp. 93–99, Mar. 1990.Google Scholar
  13. [13]
    B. Kosko, “Unsupervised learning in noise,” IEEE Trans. on Neural Networks, Vol. 1, No. 1, pp. 44–57, Mar. 1990.Google Scholar
  14. [14]
    B. Kosko, “Stochastic competitive learning,” IEEE Trans. on Neural Networks, Vol. 2, No. 5, pp. 522–529, Sept. 1991.Google Scholar
  15. [15]
    G. A. Carpenter and S. Grossberg, “ART 2: self-organization of stable category recognition codes for analog input patterns,” Applied Optics, Vol. 26, No. 23, pp. 4919–4930, Dec. 1987.Google Scholar
  16. [16]
    G. A. Carpenter and S. Grossberg, “The ART of adaptive pattern recognition by a self-organizing neural network,” IEEE Computer, Vol. 21, No. 3, pp. 77–88, Mar. 1988.Google Scholar
  17. [17]
    S. Geva and J. Sitte, “Adaptive nearest neighbor pattern classification,” IEEE Trans. on Neural Networks, Vol. 2, No.2, pp. 318–322, Mar. 1991.Google Scholar
  18. [18]
    D. L. Reilly, L. N. Cooper and C. Elbaum, “A neural model for category learning,” Biol. Cybern. 45, pp. 35–41, 1982.PubMedGoogle Scholar
  19. [19]
    Y. Okamoto, “Neural network model for real time adaptation to rapidly changing environment,” IEICE Trans., Vol. J73-D-II, No. 8, pp. 1186–1191, Aug. 1990.Google Scholar
  20. [20]
    Y. Linde, A. Buzo and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. on Communication, Vol. COM-28, No. 1, pp. 84–95, Jan. 1980.Google Scholar
  21. [21]
    P. E. Hart, “The condensed nearest neighbor rule,” IEEE Trans. on Information Theory, Vol. 14, No. 5, pp. 515–516, May 1968.Google Scholar
  22. [22]
    G. W. Gates, “The reduced nearest neighbor rule,” IEEE Trans. on Information Theory, Vol. 18, No. 5, pp. 431–433, May 1972.Google Scholar
  23. [23]
    Q. B. Xie, C. A. Laszlo and R. K. Ward, “Vector quantization technique for nonparametric classifier design,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 15. No. 12. pp. 1326–1330. Dec. 1993.Google Scholar
  24. [24]
    C. L. Chang, “Finding prototypes for nearest neighbor classifiers,” IEEE Trans. on Computers Vol. 23 No 11, pp. 1179–1184, Nov. 1974.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Qiangfu Zhao
    • 1
  • Tatsuo Higuchi
    • 1
  1. 1.Graduate School of Information SciencesTohoku UniversitySendaiJapan

Personalised recommendations