Interpretable neural networks with BP-SOM

  • Ton Weijters
  • Antal van den Bosch
  • Jaap van den Herik
Neural Networks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1398)


Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.


Hide Layer Learning Algorithm Hide Unit Neural Network Architecture Rule Extraction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. [ADT95]
    Andrews, R., Diederich, J., and Tickle, A. B. (1995). A Survey And Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks. Knowledge Based System, 8:6, 373–389.CrossRefGoogle Scholar
  2. [Hin86]
    Hinton, G. E. (1986). Learning distributed representations of concepts. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, 1–12. Hillsdale, NJ: Erlbaum.Google Scholar
  3. [Koh89]
    Kohonen, T. (1989). Self-organisation and Associative Memory. Berlin: Springer Verlag.Google Scholar
  4. [RHW86]
    Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McClelland (Eds.), Parallel Distributed Processing, Vol. 1: Foundations (pp. 318–362). Cambridge, MA: The MIT Press.Google Scholar
  5. [Thr91]
    Thrun, S. B., et. al (1991). The MONK's Problems: a performance comparison of different learning algorithms. Technical Report CMU-CS-91-197, Carnegie Mellon University.Google Scholar
  6. [Wei95]
    Weijters, A. (1995). The BP-SOM architecture and learning rule. Neural Processing Letters, 2, 13–16.Google Scholar
  7. [WVV97]
    Weijters, A., Van den Bosch, A., Van den Herik, H. J. (1997). Behavioural Aspects of Combining Backpropagation Learning and Self-organizing Maps. Connection Science, 9, 235–252.CrossRefGoogle Scholar
  8. [WVVP97]
    Weijters, A., Van den Herik, H. J., Van den Bosch, A., and Postma, E. O. (1997). Avoiding overfitting with BP-SOM. Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI'97, San Francisco, Morgan Kaufmann, 1140–1145.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Ton Weijters
    • 1
  • Antal van den Bosch
    • 2
  • Jaap van den Herik
    • 3
  1. 1.Information TechnologyEindhoven University of TechnologyThe Netherlands
  2. 2.ILK / Computational LinguisticsTilburg UniversityThe Netherlands
  3. 3.Department of Computer ScienceUniversiteit MaastrichtThe Netherlands

Personalised recommendations