Advertisement

Demand-driven concept formation

  • Stefan Wrobel
Chapter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 347)

Abstract

Most existing work on concept formation (e.g., conceptual clustering) has focused on the formation of concepts for classification purposes, resulting in an emphasis on producing sets of concepts that are complete, i.e., cover all observed instances. In this research, we are primarily concerned with concept formation as a solution to the new term problem, which results in a new set of requirements on concept formation: concept formation must be triggered in a demand-driven fashion by the shortcomings of the existing representation, and a concept's quality must be evaluated in terms of its contribution to the representation. The approach to demand-driven concept formation that we present in this paper is part of an integrated learning system called the MODELER, the learning component of the knowledge acquisition system BLIP, and is capable of forming concepts incorporating both disjunctions and relational information. Much of the power of the approach stems from its close integration with the other components of the learning system, namely, rule discovery and knowledge revision, which are also presented in this paper.

Keywords

concept formation new-term problem closed-loop learning knowledge acquisition rule discovery knowledge revision 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dietterich, T. G. and Michalski, R. S., "A Comparative Review of Selected Methods for Learning from Examples", in Machine Learning — An Artificial Intelligence Approach, Vol. I, pp. 41–82, Morgan Kaufman, Los Altos, CA, 1983.Google Scholar
  2. Easterlin, J. Daniel and Langley, Pat, "A Framework for Concept Formation", Proc. Seventh Annual Conference of the Cognitive Science Society, pp. 267–271, Irvine, CA, August 1985.Google Scholar
  3. Emde, Werner, Habel, Christopher, and Rollinger, Claus-Rainer, "Automatische Akquisition von inferentiellem Wissen" Proc. GWAI-82, 6th German Workshop on Artificial Intelligence, pp. 72–81, Springer-Verlag, Berlin, West Germany, September 1982.Google Scholar
  4. Emde, Werner, Habel, Christopher U., and Rollinger, Claus-Rainer, "The Discovery of the Equator or Concept Driven Learning", Proc. IJCAI-83, pp. 455–458, Morgan Kaufman, Los Altos, CA, 1983.Google Scholar
  5. Emde, Werner, "Non-Cumulative Learning in METAXA.3", Proc. IJCAI-87, Morgan Kaufman, Los Altos, CA, August 1987.Google Scholar
  6. Emde, Werner, "An Inference Engine for Representing Multiple Theories", this volume.Google Scholar
  7. Fisher, Douglas and Langley, Pat, "Approaches to Conceptual Clustering", Proc. IJCAI-85, pp. 691–697, Los Angeles, CA, August 1985.Google Scholar
  8. Fisher, Douglas H., "Knowledge Acquisition Via Incremental Conceptual Clustering", Machine Learning, Vol. 2, pp. 139–172, Kluwer, Boston, September 1987.Google Scholar
  9. Habel, C.U. and Rollinger, C.-R., "The Machine as Concept Learner", Proc. ECAI-82, pp. 158–159, Orsay, France, 1982.Google Scholar
  10. Hayes-Roth, Frederick, "Using Proof and Refutations to Learn From Experience", in Machine Learning — An Artificial Intelligence Approach, ed. R.S. Michalski, J.G. Carbonell, T.M. Mitchell, pp. 221–240, Tioga, Palo Alto, CA 1983.Google Scholar
  11. Kolodner, Janet L., "Reconstructive Memory: A computer model", Cognitive Science, Vol. 7, pp. 281–328, 1983.CrossRefGoogle Scholar
  12. Langley, Pat, Zytkow, Jan M., Simon, Herbert A., and Bradshaw, Gary L., "The Search for Regularity: Four Aspects of Scientific Discovery", in Machine Learning Volume II, ed. R.S. Michalski, J.G. Carbonell, T.M. Mitchell, pp. 425–469, Morgan Kaufman, Los Alots, CA, USA, 1986.Google Scholar
  13. Langley, Pat and Nordhausen, Bernd, "A Framework for Empirical Discovery", Proc. International Meeting on Advances in Learning, Les Arcs, France, 1986.Google Scholar
  14. Langley, Pat, "Editorial: On Machine Learning", Machine Learning, Vol. 1, pp. 5–10, Kluwer, Boston, 1986.Google Scholar
  15. Langley, Pat, "Machine Learning and Concept Formation", Machine Learning, Vol. 2, pp. 99–102, Kluwer, Boston, September 1987.Google Scholar
  16. Langley, Pat, Gennari, J.H., and Iba, W., "Hill-Climbing Theories of Learning", Proc. Fourth International Workshop on Machine Learning, pp. 312–323, Irvine, CA, June 1987.Google Scholar
  17. Lebowitz, Michael, "Experiments with Incremental Concept Formation: UNIMEM", Machine Learning, Vol. 2, pp. 103–138, Kluwer, Boston, September 1987.Google Scholar
  18. Lenat, Douglas B., "AM: Discovery in Mathematics as Heuristic Search", in Knowledge-Based Systems in Artificial Intelligence, ed. R. Davis and D.B. Lenat, pp. 1–225, McGraw-Hill, New York, NY, 1982.Google Scholar
  19. Michalski, Ryszard S., "A Theory and Methodology of Inductive Learning", in Machine Learning I, pp. 83–134, Morgan Kaufman, Los Altos, CA, 1983.Google Scholar
  20. Michalski, Ryszard S. and Stepp, Robert E., "Learning from Observation: Conceptual Clustering", in Machine Learning, ed. R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, Vol. I, pp. 331–363, Tioga, Palo Alto, CA, 1983.Google Scholar
  21. Michalski, Ryszard S. and Winston, Patrick H., "Variable Precision Logic", Artificial Intelligence, Vol. 29, pp. 121–146, North-Holland, Amsterdam, 1986.CrossRefGoogle Scholar
  22. Morik, Katharina, "Sloppy Modeling", this volume.Google Scholar
  23. Nordhausen, Bernd, "Conceptual Clustering Using Relational Information", Proc. AAAI-86, pp. 508–512, Morgan Kaufman, Los Altos, CA, USA, August 1986.Google Scholar
  24. Quinlan, J. Ross, "Learning Efficient Classification Procedures and Their Application to Chess End Games", in Machine Learning — An Artificial Intelligence Approach, ed. R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, pp. 463–482, Tioga, Palo Alto, CA, 1983.Google Scholar
  25. Rendell, Larry, Seshu, Raj, and Tcheng, David, "More Robust Concept Learning Using Dynamically Variable Bias", Proc. Fourth International Workshop on Machine Learning, pp. 66–78, Irvine, CA, June 1987.Google Scholar
  26. Rissland, Edwina L., "The Problem of Intelligent Example Selection", Proc. 2nd AAAI Workshop on Knowledge Acquisition for Knowledge-Based Systems, pp. 16-0–16-24, Banff, Canada, October 1987 (also to appear in the Int. Journal of Man-Machine Studies).Google Scholar
  27. Salzberg, Steven, "Heuristics for Inductive Learning", Proc. IJCAI-85, pp. 603–609, Los Angeles, CA, August 1985.Google Scholar
  28. Schlimmer, Jeffrey C., "Incremental Adjustment of Representations for Learning", Proc. Fourth International Workshop on Machine Learning, pp. 79–90, Irvine, CA, June 1987.Google Scholar
  29. Smith, Edward E. and Medin, Douglas L., "Categories and Concepts", Harvard University Press, London, England, 1981.Google Scholar
  30. Stepp, Robert E. and Michalski, Ryszard S., "Conceptual Clustering of Structured Objects: A Goal-Oriented Approach", Artificial Intelligence, Vol. 28, pp. 43–69, Elsevier Science, Amsterdam, 1986.CrossRefGoogle Scholar
  31. Stepp, Robert E., "Concepts in Conceptual Clustering", Proc. IJCAI-87, pp. 211–213, Milan, Italy, August 1987.Google Scholar
  32. Thieme, Sabine, "The Acquisition of Model Knowledge for a Model-Driven Machine Learning Approach", this volume.Google Scholar
  33. Utgoff, Paul E., "Shift of Bias for Inductive Concept Learning", in Machine Learning — An Artificial Intelligence Approach, ed. R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, Vol. II, pp. 107–148, Morgan Kaufman, Los Altos, CA, 1986.Google Scholar
  34. Wrobel, Stefan, "Design Goals for Sloppy Modeling Systems", Proc. 2nd AAAI Workshop on Knowledge Acquisition for Knowledge-Based Systems, pp. 25-0–25-17, Banff, Canada, October 1987 (also to appear in the Int. Journal of Man-Machine Studies).Google Scholar
  35. Wrobel, Stefan, "Higher-Order Concepts in a Tractable Knowledge Representation", Proc. GWAI-87 German Workshop on Artificial Intelligence, pp. 129–138, Springer-Verlag, Berlin, West Germany, September 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Stefan Wrobel
    • 1
  1. 1.Technische Universität BerlinBerlin 10West Germany

Personalised recommendations