Skip to main content
SpringerLink
Log in

Knowledge Extraction from Neural Networks Using the All-Permutations Fuzzy Rule Base: The LED Display Recognition Problem

  • Conference paper
Computational Intelligence and Bioinspired Systems (IWANN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3512))

Included in the following conference series:

Abstract

A major drawback of artificial neural networks is their black-box character. In this paper, we use the equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Cloete, I., Zurada, J.M. (eds.): Knowledge-Based Neurocomputing. MIT Press, Cambridge (2000)

    Google Scholar 

  2. Andrews, R., Diederich, J., Tickle, A.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems 8, 373–389 (1995)

    Article  Google Scholar 

  3. Tickle, A., Andrews, R., Golea, M., Diederich, J.: The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks. IEEE Trans. Neural Networks 9, 1057–1068 (1998)

    Article  Google Scholar 

  4. Tron, E., Margaliot, M.: Mathematical modeling of observed natural behavior: a fuzzy logic approach. Fuzzy Sets Systems 146, 437–450 (2004)

    Article  MATH  MathSciNet  Google Scholar 

  5. Dubois, D., Nguyen, H.T., Prade, H., Sugeno, M.: Introduction: The real contribution of fuzzy systems. In: Nguyen, H.T., Sugeno, M. (eds.) Fuzzy Systems: Modeling and Control, pp. 1–17. Kluwer, Dordrecht (1998)

    Google Scholar 

  6. Zadeh, L.A.: Fuzzy logic = computing with words. IEEE Trans. Fuzzy Systems 4, 103–111 (1996)

    Article  Google Scholar 

  7. McGarry, K., Wermter, S., MacIntyre, J.: Hybrid neural systems: from simple coupling to fully integrated neural networks. Neural Computing Surveys 2, 62–93 (1999)

    Google Scholar 

  8. Mitra, S., Hayashi, Y.: Neuro-fuzzy rule generation: survey in soft computing framework. IEEE Trans. Neural Networks 11, 748–768 (2000)

    Article  Google Scholar 

  9. Jang, J.S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice-Hall, Englewood Cliffs (1997)

    Google Scholar 

  10. Fu, L.M., Fu, L.C.: Mapping rule based systems into neural architectures. Knowledge Based Systems 3, 48–56 (1990)

    Article  Google Scholar 

  11. Jang, J.S.R., Sun, C.T.: Functional equivalence between radial basis function networks and fuzzy inference systems. IEEE Trans. Neural Networks 4, 156–159 (1993)

    Article  Google Scholar 

  12. Benitez, J.M., Castro, J.L., Requena, I.: Are artificial neural networks black boxes? IEEE Trans. Neural Networks 8, 1156–1164 (1997)

    Article  Google Scholar 

  13. Castro, J.L., Mantas, C.J., Benitez, J.M.: Interpretation of artificial neural networks by means of fuzzy rules. IEEE Trans. Neural Networks 13, 101–116 (2002)

    Article  Google Scholar 

  14. Zhang, D., Bai, X.L., Cai, K.Y.: Extended neuro-fuzzy models of multilayer perceptrons. Fuzzy Sets Systems 142, 221–242 (2004)

    Article  MATH  MathSciNet  Google Scholar 

  15. Kolman, E., Margaliot, M.: Are artificial neural networks white boxes? IEEE Trans. Neural Networks (to appear) (Online) Available: www.eng.tau.ac.il/~michaelm

  16. Kolman, E., Margaliot, M.: Neural networks = fuzzy rule bases. In: Ruan, D., et al. (eds.) Applied Computational Intelligence – Proceedings of the 6th International FLINS Conference, pp. 111–117. World Scientific, Singapore (2004)

    Chapter  Google Scholar 

  17. Kolman, E., Margaliot, M.: Knowledge extraction from neural networks using the all-permutations fuzzy rule base (submitted) (Online) Available: www.eng.tau.ac.il/~michaelm

  18. Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth International Group, ch. 2 (1984)

    Google Scholar 

  19. Aha, D.W., Kibler, D., Albert, M.K.: Instance-based learning algorithms. Machine Learning 6, 37–66 (1991)

    Google Scholar 

  20. Boger, Z., Guterman, H.: Knowledge extraction from artificial neural networks models. In: Proc. IEEE Int. Conf. Systems, Man and Cybernetics (SMC 1997), Orlando, Florida, pp. 3030–3035 (1997)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Electrical Engineering, Tel-Aviv University, Tel-Aviv, 69978, Israel

    Eyal Kolman & Michael Margaliot

Authors
  1. Eyal Kolman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michael Margaliot
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Departamento de Ingeniería Electrónica, Universitat Politècnica de Catalunya (UPC). E.T.S.I. de Telecomunicación, Campus Norte, Edificio C4, C/ Jordi Girona, 1-3, E08034, Barcelona, Spain

    Joan Cabestany

  2. Department of Computer Architecture and Computer Technology, University of Granada,  

    Alberto Prieto

  3. Grupo ISIS, Dpto. Tecnología Electrónica ETSI Telecomunicación, Universidad de Málaga, Campus de Teatinos, 29071, Málaga, Spain

    Francisco Sandoval

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kolman, E., Margaliot, M. (2005). Knowledge Extraction from Neural Networks Using the All-Permutations Fuzzy Rule Base: The LED Display Recognition Problem. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_150

Download citation

  • DOI: https://doi.org/10.1007/11494669_150

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-26208-4

  • Online ISBN: 978-3-540-32106-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation