Effectively Extracting Rules from Trained Neural Networks Based on the New Measurement Method of the Classification Power of Attributes

  • Dexian Zhang
  • Yang Liu
  • Ziqiang Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3614)


The major problems of currently used approaches for extracting symbolic rules from trained neural networks are analyzed. The lack of efficient heuristic information is the fundamental reason that causes the low effectiveness of currently used approaches. In this paper, a new measurement method of the classification power of attributes on the basis of differential information of the trained neural networks is proposed, which is suitable for both continuous attributes and discrete attributes. Based on this new measurement method, a new approach for rule extraction from trained neural networks and classification problems with continuous attributes is proposed. The performance of the new approach is demonstrated by several computing cases. The experimental results prove that the approach proposed can improve the validity of the extracted rules remarkably compared with other rule extracting approaches, especially for the complicated classification problems.


Continuous Attribute Heuristic Information Trained Neural Network Discrete Attribute Symbolic Rule 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fu, L.: Rule generation from neural networks. IEEE Trans. Systems Man. Cybernet 24, 1114–1124 (1994)CrossRefGoogle Scholar
  2. 2.
    Towell, G.G., Shavlik, J.W.: Extracting refined rules from knowledge-based neural networks. Machine Learning 13, 71–101 (1993)Google Scholar
  3. 3.
    Lu, H.J., Setiono, R.: NeuroRule: a connectionist approach to data mining. In: Proceedings of 21th International Conference on Very Large Data Bases, Zurich, Switzerland, pp. 478–489 (1995)Google Scholar
  4. 4.
    Zhou, Z.H., Jiang, Y., Chen, S.F.: Extracting symbolic rules from trained neural network ensembles. AI Communications 16, 3–15 (2003)Google Scholar
  5. 5.
    Sestito, S., Dillon, T.: Knowledge acquisition of conjunctive rules using multilayered neural networks. International Journal of Intelligent Systems 8, 779–805 (1993)CrossRefGoogle Scholar
  6. 6.
    Craven, M.W., Shavlik, J.W.: Using sampling and queries to extract rules from trained neural networks. In: Proceedings of the 11th International Conference on Machine Learning, New Brunswick, USA, pp. 37–45 (1994)Google Scholar
  7. 7.
    Maire, F.: Rule-extraction by backpropagation of polyhedra. Neural Networks 12, 717–725 (1999)CrossRefGoogle Scholar
  8. 8.
    Setiono, R., Leow, W.K.: On mapping decision trees and neural networks. Knowledge Based Systems 12, 95–99 (1999)CrossRefGoogle Scholar
  9. 9.
    Kamarthi, S.V., Pittner, S.: Accelerating neural network training using weight extrapolation. Neural Networks 12, 1285–1299 (1999)CrossRefGoogle Scholar
  10. 10.
    Fu, X.J., Wang, L.P.: Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance. IEEE Trans. System, Man, Cybern, Part B-Cybernetics 33, 399–409 (2003)CrossRefGoogle Scholar
  11. 11.
    Blake, C., Keogh, E., Merz, C.J.: UCI repository of machine learning databases. Department of Information and Computer Science, University of California,Irvine,CA,USA, (1998),

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Dexian Zhang
    • 1
  • Yang Liu
    • 2
  • Ziqiang Wang
    • 1
  1. 1.School of Information Science and EngineeringHenan University of TechnologyZheng ZhouChina
  2. 2.Computer CollegeNorthwestern Polytecnical UniversityXi’anP.R.C(China)

Personalised recommendations