Input understanding as a basis for multistrategy task-adaptive learning

  • Gheorghe Tecuci
  • Ryszard S. Michalski
Communications Learning and Adaptive Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 542)


The paper explores several general issues in developing a multistrategy task-adaptive learning (MTL) system. The system aims at integrating a whole range of learning strategies, such as explanation-based learning, empirical generalization, abduction, constructive induction, learning by analogy and abstraction. The integration is dynamic, i.e. the way different strategies are evoked depends on the learning task at hand. The key idea of the learning method is that the learner tries to “understand” the input in terms of its current knowledge, and then uses this understanding to improve the knowledge. This process may involve both certain and plausible reasoning. The paper extends and generalizes the previous work on this topic.


multistrategy learning induction analogy abduction abstraction explanation-based learning knowledge acquisition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Birnbaum, L., and Collins, G. (eds.), Machine Learning: Proceedings of the Eighth International Workshop, San Mateo, CA, Morgan Kaufmann, 1991.Google Scholar
  2. Collins, A., and Michalski, R.S., The Logic of Plausible Reasoning: A Core Theory, Cognitive Science, Vol. 13, No. 1, pp.1–49, 1989.Google Scholar
  3. Davies T.R., and Russell S.J., A Logical Approach to Reasoning by Analogy, Proceedings of IJCAI-87, pp. 264–270, Milan, Italy, 1987.Google Scholar
  4. DeJong, G. and Mooney, R., Explanation-Based Learning: An Alternative View, Machine Learning Journal, vol 2, 1986.Google Scholar
  5. DeJong, G., Explanation-based Learning with Plausible Inferencing, Proceedings of the Fourth European Working Session on Learning (EWSL89), Montpellier, France, 1989.Google Scholar
  6. Michalski, R. S., Theory and Methodology of Inductive Learning, Machine Learning: An Artificial Intelligence Approach, R.S.Michalski, J.G.Carbonell, T.M.Mitchell (Eds.), Tioga Publishing Co., 1983.Google Scholar
  7. Michalski, R.S., Toward a Unified Theory of Learning: Multistrategy Task-Adaptive Learning, in Reports of Machine Learning and Inference, MLI 90-1, Center for Artificial Intelligence, George Mason University, January 1990.Google Scholar
  8. Mitchell, T.M., Keller, T., and Kedar-Cabelli, S., Explanation-Based Generalization: A Unifying View, Machine Learning Journal, Vol. 1, January 1986.Google Scholar
  9. Mooney R., Bennet S., A Domain Independent Explanation Based Generalizer, in Proceedings AAAI-86, Philadelphia, 1986, pp.551–555.Google Scholar
  10. Tecuci G., DISCIPLE: A Theory, Methodology, and System for Learning Expert Knowledge, Ph.D. Thesis, University of Paris-South, 1988.Google Scholar
  11. Tecuci G. and Kodratoff Y., Apprenticeship Learning in Imperfect Theory Domains, in Machine Learning: An Artificial Intelligence Approach vol. III, Morgan Kaufmann, 1990.Google Scholar
  12. Tecuci G., and Michalski R.S., A Method for Multistrategy Task-adaptive Learning Based on Plausible Justifications, in Birnbaum L., and Collins G. (eds), Machine Learning: Proceedings of the Eighth International Workshop, Chicago, June 1991, Morgan Kaufmann, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Gheorghe Tecuci
    • 1
  • Ryszard S. Michalski
    • 1
  1. 1.Center for Artificial Intelligence and Department of Computer ScienceGeorge Mason UniversityFairfaxUSA

Personalised recommendations