Task decomposition based on class relations: A modular neural network architecture for pattern classification

  • Bao-Liang Lu
  • Masami Ito
Formal Tools and Computational Models of Neurons and Neural Net Architectures
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1240)


In this paper, we propose a new methodology for decomposing pattern classification problems based on the class relations among training data. We also propose two combination principles for integrating individual modules to solve the original problem. By using the decomposition methodology, we can divide a K-class classification problem into \(\left( {\begin{array}{*{20}c}K \\2 \\\end{array} } \right)\) relatively smaller two-class classification problems. If the twoclass problems are still hard to be learned, we can further break down them into a set of smaller and simpler two-class problems. Each of the two-class problem can be learned by a modular network independently. After learning, we can easily integrate all of the modules according to the combination principles to get the solution of the original problem. Consequently, a K-class classification problem can be solved effortlessly by learning a set of smaller and simpler two-class classification problems in parallel.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Anand, R., Mehrotra, K. G., Mohan, C. K., and Ranka, S.: Efficient classification for multiclass problems using modular neural networks, IEEE Transaction on Neural Networks, 1995, 6(1), 117–124.Google Scholar
  2. 2.
    Jacobs, R. A., Jordan, M. I., Nowlan, M. I., and Hinton, G. E.: Adaptive mixtures of local experts, Neural Computation, 1991, 3, 79–87.Google Scholar
  3. 3.
    Hrycej, T.: Modular Learning in Neural Networks, 1992, John-Wiley & Sons, Inc.Google Scholar
  4. 4.
    Jenkins, R., and Yuhas, B.: A simplified neural network solution through problem decomposition: The case of the truck backer-upper, IEEE Transaction on Neural Networks, 1993, 4(4), 718–722.Google Scholar
  5. 5.
    Lang, K., and Witbrock, M.: Learning to tell two spirals apart, Proceedings of 1988 Connectionist Models Summer School, 1988, 52–59. Morgan Kaufmann.Google Scholar
  6. 6.
    Lu, B. L., Bai, Y., Kita, H., and Nishikawa, Y.: An efficient multilayer quadratic perceptron for pattern classification and function approximation, Proceedings. of International Joint Conference on Neural Networks, Nagoya, 1993, 1385–1388.Google Scholar
  7. 7.
    Lu, B.-L., Kita, H., and Nishikawa, Y.: A multi-sieving neural network architecture that decomposes learning tasks automatically, Proceedings of IEEE Conference on Neural Networks, 1994, 1319–1324.Google Scholar
  8. 8.
    Murre, J. M. J.: Learning and Categorization in Modular Neural Networks, 1992, Harvester Wheatsheaf.Google Scholar
  9. 9.
    Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: Learning internal representations by error propagation, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1996, 1, D. E. Rumelhart, J. L. McClelland, and PDP Research Group eds, MIT Press.Google Scholar
  10. 10.
    Thiria, S., Mejia, C., Badran, F., and Crepon, M.: Multimodular architecture for remote sensing operations, Advances in Neural Information processing Systems 4 1992, 675–682.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Bao-Liang Lu
    • 1
  • Masami Ito
    • 1
  1. 1.Bio-Mimetic Control Research CenterThe Institute of Physical and Chemical Research (RIKEN)NagoyaJapan

Personalised recommendations