An Enhanced Fuzzy Neural Network

  • Kwang Baek Kim
  • Young-Hoon Joo
  • Jae-Hyun Cho
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3320)


In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the proposed method to the problem of recognizing ID number in identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hecht-Nielse, R.: Theory of Backpropagation Neural Networks. In: Proceedings of IJCNN, vol. 1, pp. 593–605 (1998)Google Scholar
  2. 2.
    Hirose, Y., Yamashita, K., Hijihya, S.: Backpropagation Algorithm Which Varies the Number of Hidden Units. Neural Networks 4, 61–66 (1991)CrossRefGoogle Scholar
  3. 3.
    Kim, K.B., Kang, M.H., Cha, E.Y.: Fuzzy Competitive Backpropagation using Nervous System. In: Proceedings of WCSS, pp. 188–193 (1997)Google Scholar
  4. 4.
    Kim, K.B., Kim, Y.J.: Recognition of English Calling Cards by Using Enhanced Fuzzy Radial Basis Function Neural Networks. IEICE Trans. Fundamentals E87-A(6), 1355–1362 (2004)Google Scholar
  5. 5.
    Saito, T., Mukaidono, M.: A Learning algorithm for Max-Min Network and its Application to Solve Relation Equations. In: Proceedings of IFSA, pp. 184–187 (1991)Google Scholar
  6. 6.
    Kim, T.K., Yun, H.G., Lho, Y.W., Kim, K.B.: An Educational Matters Administration System on The Web by Using Image Recognition. In: Proceedings of Korea Intelligent Information Systems, pp. 203–209 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Kwang Baek Kim
    • 1
  • Young-Hoon Joo
    • 2
  • Jae-Hyun Cho
    • 3
  1. 1.Dept. of Computer EngineeringSilla UniversityS. Korea
  2. 2.School of Electronic and Information EngneeringKunsan National UniversityS. Korea
  3. 3.Dept. of Computer InformationCatholic University of PusanS. Korea

Personalised recommendations