Efficient learning in Multi-Layered Perceptron using the Grow-And-Learn algorithm

  • Gildas Cherruel
  • Bassel Solaiman
  • Yvon Autret
Posters Theory of Computation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 990)


The well-known Multi-Layered Perceptron has gained power thanks to the Back Propagation Algorithm. The difficulty which still subsists is its time-wasting. In fact, the learning process can be improved by using the Grow-And-Learn (GAL) algorithm. In this paper, we present such a hybrid system: the cooperation between GAL and MLP networks. The obtained system is more rapid and more efficient than the classic Back Propagation which computes on the MLP.


character recognition co-operation neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Y. L. Cun, “Generalization and network design strategies,” technical report crg-tr-89-4, University of Toronto, 1989.Google Scholar
  2. 2.
    N. Ohnishi, A. Okamoto, and N. Sugie, “Selective presentation of learning samples for efficient learning in multi-layered perceptron,” Proceedings of the International Joint Conference on Neural Networks, vol. 1, pp. 278–289, Jan. 1990.Google Scholar
  3. 3.
    E. Alpaydin, “Grow-And-Learn: an incremental method for category learning,” Proceedings of the International Conference on Neural Networks, pp. 761–764, July 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Gildas Cherruel
    • 1
    • 2
  • Bassel Solaiman
    • 3
  • Yvon Autret
    • 1
  1. 1.Laboratoire LIMIUniversité de Bretagne OccidentaleBrest CedexFrance
  2. 2.TNIBrestFrance
  3. 3.Département Image et Traitement de l'InformationENSTBBrest CedexFrance

Personalised recommendations