Applied Intelligence

, Volume 12, Issue 1–2, pp 7–13 | Cite as

Neural Networks and Structured Knowledge: Rule Extraction and Applications

  • Franz J. Kurfess
Article

Abstract

As the second part of a special issue on “Neural Networks and Structured Knowledge,” the contributions collected here concentrate on the extraction of knowledge, particularly in the form of rules, from neural networks, and on applications relying on the representation and processing of structured knowledge by neural networks. The transformation of the low-level internal representation in a neural network into higher-level knowledge or information that can be interpreted more easily by humans and integrated with symbol-oriented mechanisms is the subject of the first group of papers. The second group of papers uses specific applications as starting point, and describes approaches based on neural networks for the knowledge representation required to solve crucial tasks in the respective application.

The companion first part of the special issue [1] contains papers dealing with representation and reasoning issues on the basis of neural networks.

neural networks rule extraction knowledge representation structured knowledge connectionism hybrid systems 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    F.J. Kurfeß, Special issue on “Neural Networks and Structured Knowledge: Representation and Reasoning” (guest editor), Applied Intelligence, vol. 11, no. 1, 1999.Google Scholar
  2. 2.
    J. Denker, D. Schwartz, B. Wittner, S. Solla, R. Howard, L. Jacket, and J. Hopfield, “Automatic learning, rule extraction and generalization,” Complex Systems, vol. 1, no. 5, pp. 877–922, 1987.Google Scholar
  3. 3.
    J.-S. Roger Jang, “Rule extraction using generalized neural networks,” in Proc. of the 4th IFSA World Congress(in the Volume for Artificial Intelligence), July 1991, pp. 82–86.Google Scholar
  4. 4.
    C. McMillan, M.C. Mozer, and P. Smolensky, “The connectionist science game: Rule extraction and refinement in a neural network,” in Proceedings of the 13th Annual Conference of the Cognitive Science Society, 1991.Google Scholar
  5. 5.
    R. Setiono and H. Liu, “Understanding neural networks via rule extraction,” edited by Chris S. Mellish, in Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, San Mateo, August 20–25, 1995, Morgan Kaufmann, pp. 480–487.Google Scholar
  6. 6.
    R. Andrews and J. Diederich (Eds.), Rule Extraction Workshop, Neural Information Processing Systems (NIPS) 9, 1996.Google Scholar
  7. 7.
    R. Andrews, J. Diederich, and A.B. Tickle, “Survey and critique of techniques for extracting rules from trained artificial neural networks,” Knowledge Based Systems, vol. 8, no. 6, pp. 373–389, December 1995.Google Scholar
  8. 8.
    J. Köbler, U. Schöning, and J. Toran, The Graph Isomorphism Problem: Its Structural Complexity, Birkhäuser: Boston, 1993.Google Scholar
  9. 9.
    A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K.J. Lang, “Phoneme recognition using time-delay neural networks,” IEEE Transactions on Acoustics, Speech, & Signal Processing, vol. 37, no. 3, pp. 328–339, 1989.Google Scholar
  10. 10.
    K. Schädler and F. Wysotzki, “Comparing structures using a hopfield-style network,” Applied Intelligence, vol. 11, no. 1, pp. 15–30, 1999.Google Scholar
  11. 11.
    P. Myllymäki, “Massively parallel probabilistic reasoning with boltzmann machines,” Applied Intelligence, vol. 11, no. 1, pp. 31–44, 1999.Google Scholar
  12. 12.
    S. Hölldobler, Y. Kalinke, and H.-P. Störr, “Approximating the semantics of logic programs by recurrent neural networks,” Applied Intelligence, vol. 11, no. 1, pp. 45–58, 1999.Google Scholar
  13. 13.
    A.S. d'Avila Garcez and G. Zaverucha, “The connectionist inductive learning and logic programming system,” Applied Intelligence, vol. 11, no. 1, pp. 59–78, 1999.Google Scholar
  14. 14.
    L. Shastri, “Advances in SHRUTI—a neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony,” Applied Intelligence, vol. 11, no. 1, pp. 79–108, 1999.Google Scholar
  15. 15.
    R. Sun, T. Peterson, and E. Merrill, “Ahybrid architecture for situated learning of reactive sequential decision making,” Applied Intelligence, vol. 11, no. 1, pp. 109–127, 1999.Google Scholar
  16. 16.
    F.J. Kurfeß (Ed.), Neural Networks and Structured Knowledge, European Coordinating Committee for Artificial Intelligence (ECCAI), European Conference on Artificial Intelligence (ECAI '96), Workshop Proceedings, Budapest, 1996.Google Scholar
  17. 17.
    R. Sun and F. Alexandre (Eds.), Connectionist-Symbolic Integration, Lawrence Erlbaum, 1997.Google Scholar
  18. 18.
    G. Paaß and F.J. Kurfeß (Eds.), Wissensverarbeitung mit neuronalen Netzen (Knowledge Processing with Neural Networks), number 221 in GMD-Studien, Schloß Birlinghoven, 53757 Sankt Augustin, Germany, September 1993, Gesellschaft für Mathematik und Datenverarbeitung (GMD), Workshop KI'Google Scholar
  19. 19.
    G. Paaß and F.J. Kurfeß, Wissensverarbeitung mit neuronalen Netzen, O. Herzog, T. Christaller, and D. Schütt (Eds.), in Grundlagen und Anwendungen der Künstlichen Intelligenz-17, Fachtagung für Künstliche Intelligenz (KI '93), Informatik aktuell, Subreihe Künstliche Intelligenz, Springer Verlag, Berlin, pp. 217–225, 1993.Google Scholar
  20. 20.
    F.J. Kurfeß and G. Paaß (Eds.), Integration Neuronaler und Wissensbasierter Ansätze, number 242 in GMD-Studien, D-53754 Sankt Augustin, September 1994, Gesellschaft für Informatik (GI), Gesellschaft für Mathematik und Datenverarbeitung (GMD), Workshop at the KI '94 Conference, Saarbrücken, Germany.Google Scholar
  21. 21.
    I. Duwe, F.J. Kurfeß, G. Paaß, and S. Vogel (Eds.), Konnektionismus und neuronale Netze—Beiträge zur Herbstschule HeKoNN 94, number 242 in GMD-Studien, D-53754 Sankt Augustin, Oktober 1994.Google Scholar
  22. 22.
    F.J. Kurfeß,Wissensverarbeitung mit neuronalen Netzen, edited by G. Dorffner, K. Möller, G. Paaß, and S. Vogel, in Konnektionismus und neuronale Netze—Beiträge zur Herbstschule HeKoNN '95, GMD-Studien, D-53754 Sankt Augustin, Oktober 1995, Gesellschaft für Mathematik und Datenverarbeitung (GMD), pp. 211–223.Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Franz J. Kurfess
    • 1
  1. 1.Department of Computer ScienceConcordia UniversityMontreal, QuebecCanada

Personalised recommendations