Skip to main content
SpringerLink
Log in
Book cover

Knowledge Representation and Organization in Machine Learning pp 258–288Cite as

Creating high level knowledge structures from simple elements

  • Chapter
  • First Online:

  • 198 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 347))

Abstract

In spite of the limitations of OCCAM's language capabilities, I believe that the approach outlined in this paper is a promising means of creating knowledge-based systems to perform useful functions. The approach consists of using similarity-based learning to acquire general schemata which represent plans for achieving goals. These schemata are specialized with explanation-based learning to create a memory which indicates the conditions under which the plans for achieving goals have proved successful. Explanation-based learning in OCCAM makes use of the representation for complex plans which is created by the similarity-based learning process. The schemata formed by explanation-based learning serve as efficient means of recognizing the class of situations which would have the same explanation as a training example.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bartlett, F.. Remembering: A study in experimental and social psychology. Cambridge University Press, New York, 1932.

    Google Scholar 

  2. Birnbaum, L. & Selfridge, M. Conceptual analysis of natural language. In Inside computer understanding: Five programs plus miniatures, Schank, R., & Riesbeck, C., Ed., Lawrence Erlbaum Associates, Hillsdale, NJ., 1981, pp. 318–354.

    Google Scholar 

  3. Bobrow, D.G., Kaplan, R., Kay, M., Norman, D., Thompson, H.S., & Winograd, T. GUS, A frame-driven dialog system. Artificial Intelligence 8, 1 (1977), 155–173.

    Article  Google Scholar 

  4. Bower, G., Black, J. & Turner, T. Scripts in Memory for Text. Cognitive Psychology 11 (1979), 171–216.

    Article  Google Scholar 

  5. Brachman, R., & Schmolze, J. An overview of the KL-ONE knowledge Representation System. Cognitive Science 9, 2 (1985), 171–216.

    Google Scholar 

  6. Bruner, J.S., Goodnow, J.J., & Austin, G.A.. A Study of Thinking. Wiley, New York, 1956.

    Google Scholar 

  7. Cullingford, R. E. Script Application: Computer Understanding of Newspaper Stories. Computer Science Research Report 116, Yale University, 1976.

    Google Scholar 

  8. Diettrich, T. Learning at the knowledge level. Machine Learning 1, 3 (1986), 287–315.

    Google Scholar 

  9. Dyer, M.. In Depth Understanding. MIT Press, 1983.

    Google Scholar 

  10. Fikes, R., Hart, R., & Nilsson, N. Learning and executing generalized robot plans. Artificial Intelligence 3 (1972), 251–288.

    Article  Google Scholar 

  11. Graesser, A., Gordon, S., and Sawyer, J. Recognition Memory for typical and atypical actions in scriptal activities: Tests of a script pointer + tag hypothesis. Journal of Verbal Learning and Verbal Behavior 18 (1979), 319–332.

    Article  Google Scholar 

  12. Hirsh, H. Explanation-based learning in a logic programming environment. Proceedings of the Tenth International Joint Conference on Artificial Intelligence, Milan, Italy, 1987, pp. 221–227.

    Google Scholar 

  13. Hufbauer, G. & Schott, J.. Economic Sanctions Reconsidered: History and Current Policy. Institute For International Economics, Washington, D.C., 1985.

    Google Scholar 

  14. Kedar-Cabelli, S. Explanation-based generalization as resolution theorem proving. Proceedings of the Fourth International Machine Learning Workshop, Irvine, CA, 1987, pp. 383–387.

    Google Scholar 

  15. Keller, R. Defining operationality for explanation-based learning. Proceedings of the National Conference on Artificial Intelligence, Seattle, WA., 1987, pp. 482–487.

    Google Scholar 

  16. Kolodner, J. Retrieval and organizational strategies in conceptual memory: A computer model. Lawrence Erlbaum Associates, Hillsdale, NJ., 1984.

    Google Scholar 

  17. Laird, J., Rosenbloom, P., and Newell, A. Chunking in Soar: The anatomy of a general learning mechanism. Machine Learning 1, 1 (1986), 11–46.

    Google Scholar 

  18. Lebowitz, M. Generalization and memory in an integrated understanding system. Computer Science Research Report 186, Yale University, 1980.

    Google Scholar 

  19. Lebowitz, M. Correcting erroneous generalizations. Cognition and Brain Theory 5, 4 (1982), 367–381.

    Google Scholar 

  20. Michalski, R. & Ko, H. On the nature of explanation or Why did the wine bottle shatter. Proceedings of the AAAI Symposium on Explanation-Based Learning, Geseke, Germany, 1988, pp. 12–17.

    Google Scholar 

  21. Minsky, M. A Framework for Representing Knowledge. In The Psychology of Computer Vision, Winston, P.H., Ed., McGraw-Hill, New York, NY, 1975, pp. 211–277.

    Google Scholar 

  22. Mitchell, T., Kedar-Cabelli, S. & Keller, R. Explanation-based learning: A unifying view. Machine Learning 1, 1 (1986), 47–80.

    Google Scholar 

  23. Mooney, R. & Bennett, S. A domain independent explanation-based generalizer. Proceedings of the Ninth International Joint Conference on Artificial Intelligence, Los Angeles, CA, 1985, pp. 551–560.

    Google Scholar 

  24. Mostow, J. Searching for operational concept descriptions in BAR, MetaLex, and EBG. Proceedings of the Fourth International Machine Learning Workshop, Irvine, CA, 1987, pp. 376–382.

    Google Scholar 

  25. Pazzani, M. Interactive Script Instantiation. Proceedings of the National Conference on Artificial Intelligence, Washington, D.C., 1983, pp. 320–326.

    Google Scholar 

  26. Pazzani, M., Dyer, M. & Flowers, M. The role of prior causal theories in generalization. Proceedings of the National Conference on Artificial Intelligence, American Association for Artificial Intelligence, 1986, pp. 545–550.

    Google Scholar 

  27. Pazzani, M. Inducing causal and social theories: A prerequisite for explanation-based learning. Proceedings of the Fourth International Machine Learning Workshop, Irvine, CA, 1987, pp. 230–241.

    Google Scholar 

  28. Pazzani, M.J. Learning causal relationships: An integration of empirical and explanation-based learning methods. Ph.D. Th., University of California, Los Angeles, 1988.

    Google Scholar 

  29. Roberts, R. & Goldstein, I. The FRL Manual. MIT Al Lab. Memo 409, MIT, 1977.

    Google Scholar 

  30. Rosenbloom, P. & Laird, J. Mapping explanation-based generalization onto Soar. Proceedings of the National Conference on Artificial Intelligence, American Association for Artificial Intelligence, 1986, pp. 561–567.

    Google Scholar 

  31. Schank, R. & Abelson, R., Scripts, plans, goals, and understanding. Lawrence Erlbaum Associates, Hillsdale, NJ., 1977.

    Google Scholar 

  32. Swartout, W. Explanation: A source of guidance for knowledge representation. This volume, 1988.

    Google Scholar 

  33. Waldinger, R. Achieving several goals simultaneously. Machine Intelligence 8 (1977), 94–130.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. UCLA Artificial Intelligence Laboratory, 3531 Boelter Hall, 90024, Los Angeles, CA, USA

    Michael Pazzani

Authors
  1. Michael Pazzani
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Katharina Morik

Rights and permissions

Reprints and permissions

Copyright information

© 1989 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Pazzani, M. (1989). Creating high level knowledge structures from simple elements. In: Morik, K. (eds) Knowledge Representation and Organization in Machine Learning. Lecture Notes in Computer Science, vol 347. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017227

Download citation

  • DOI: https://doi.org/10.1007/BFb0017227

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-50768-0

  • Online ISBN: 978-3-540-46081-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation