Skip to main content
SpringerLink
Log in

Pedagogical Method for Extraction of Symbolic Knowledge

  • Conference paper
  • First Online:
Rough Sets and Current Trends in Computing (RSCTC 1998)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1424))

Included in the following conference series:

Abstract

This paper addresses the extraction of symbolic knowledge from trained artificial neural networks. Specifically, for that purpose the so-called pedagogical approach is incorporated, where the trained network is used as an oracle when inducing the symbolic description. We present an essential extension of the Trepan algorithm proposed originally by Craven and Shavlik [4][5]. The crucial modification concerns the way of generating artificial training instances. The paper ends with an empirical verification of the proposed method on popular machine learning benchmarks and comparison with the original Trepan.

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 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

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. Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth and Brooks (1984)

    Google Scholar 

  2. Partridge, D., Wilks, Y. (eds.): The Foundations of Artificial Intelligence. A Sourcebook. Cambridge Univ. Press (1990)

    Google Scholar 

  3. Craven, M.W., Shavlik, J.W.: Using Sampling and Queries to Extract Rules from Trained Neural Networks. In: Proc. Eleventh Int. Conf. on Machine Learning, Morgan Kaufmann (1994)

    Google Scholar 

  4. Craven, M.W., Shavlik, J.W.: Extracting Tree-Structured Representations of Trained Networks. In: Touretzky, D., Mozer, M., Hasselmo, M. (eds.): Advances in Neural Information Processing Systems (vol. 8), MIT Press, Cambridge (1996)

    Google Scholar 

  5. Craven, M.W.: Extracting Comprehensible Models from Trained Neural Networks. Ph.D. Thesis, Comp. Sci. Dept., Univ. of Wisconsin-Madison (1996)

    Google Scholar 

  6. Diederich, J.: Explanation and artificial neural networks. Int. J. Man-Machine Studies 37 (1992) 335–355

    Article  Google Scholar 

  7. Dinsmore, J. (ed.): The Symbolic and Connectionist Paradigms: Closing the Gap. Lawrence Erlbaum Associates (1992)

    Google Scholar 

  8. Fu, L.: Rule Generation from Neural Networks. IEEE Trans. SMC-24 (1994)

    Google Scholar 

  9. Gallant, S.I.: Connectionist expert systems. Comm. of the ACM 31 (1988) 152–169

    Article  Google Scholar 

  10. Hayashi, Y.: A neural expert system with automated extraction of fuzzy if-then rules and its application to medical diagnosis. In: Advances in Neural Information Processing Systems (vol. 3). Morgan Kaufmann (1990)

    Google Scholar 

  11. Merz, C.J., Murphy, P.M.: Repository of machine learning databases. Univ. of California, Dept. of Information and Comp. Sci. (1996)

    Google Scholar 

  12. Murphy, P.M., Pazzani, M.J.: ID2-of-3: Constructive induction of M-of-N concepts for discriminators in decision trees. Proc. Eighth Int. Machine Learning Workshop, Morgan Kaufmann (1991)

    Google Scholar 

  13. Quinlan, J.R.: Induction of Decision Trees. Machine Learning 1 (1986) 81–106

    Google Scholar 

  14. Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann (1993)

    Google Scholar 

  15. Riedmiller, M., Braun, H.: RPROP-A Fast Adaptive Learning Algorithm. Technical Report, Univ. Karlsruhe (1992)

    Google Scholar 

  16. Słowiński, R., Stefanowski, J., Susmaga, R.: Rough set analysis of attribute dependencies in technical diagnosis. Proc. 4th Intl. Workshop on Rough Sets, Fuzzy Sets, and Machine Discovery, Univ. of Tokyo (1996)

    Google Scholar 

  17. Szcześniak, I.: Acquisition of symbolic knowledge from neural networks. M.Sc. Thesis, Inst. of Comp. Sci., Poznań Univ. of Tech. (1997)

    Google Scholar 

  18. Thrun, S.B.: Extracting provably correct rules from artificial neural networks. Technical Report IAI-TR-93-5, Institut für Informatik, Univ. Bonn (1993)

    Google Scholar 

  19. Towell, G.G., Shavlik, J.W.: Knowledge-Based Artificial Neural Networks. Artificial Intelligence 70 (1994) 119–165

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60-965, Poznań, Poland

    Krzysztof Krawiec, Roman Słowiński & Irmina Szcześniak

Authors
  1. Krzysztof Krawiec
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Roman Słowiński
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Irmina Szcześniak
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute of Mathematics, Warsaw University of Technology, Pl. Politechniki 1, 00-665, Warszawa, Poland

    Lech Polkowski

  2. Institute of Mathematics, Warsaw University, Banacha 2, 02-097, Warszawa, Poland

    Andrzej Skowron

Rights and permissions

Reprints and permissions

Copyright information

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Krawiec, K., Słowiński, R., Szcześniak, I. (1998). Pedagogical Method for Extraction of Symbolic Knowledge. In: Polkowski, L., Skowron, A. (eds) Rough Sets and Current Trends in Computing. RSCTC 1998. Lecture Notes in Computer Science(), vol 1424. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-69115-4_60

Download citation

  • DOI: https://doi.org/10.1007/3-540-69115-4_60

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-64655-6

  • Online ISBN: 978-3-540-69115-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation