Advertisement

Algebraic structure of some learning systems

  • Jean-Gabriel Ganascia
Selected Papers New Learning Paradigms
Part of the Lecture Notes in Computer Science book series (LNCS, volume 744)

Abstract

The goal of this research is to define some general properties of representation languages, e.g. lattice structures, distributive lattice structures, cylindric algebras, etc. to which generalization algorithms could be related. This paper introduces a formal framework providing a clear description of version space. It is of great theoretical interest since it makes the generalization and comparison of many machines learning algorithms possible. Moreover, it could lead to reconsider some aspects of the classical description of version space. In this paper, the scope of investigation will be restricted to lattices — i.e. to cases where there exists one and only one generalization for any set of examples — and in particular to Brouwerian lattices. It is shown that a particularly interesting case covered by this restriction is the product of hierarchical posets which is equivalent to the conjunction of tree structured or linearly ordered attributes.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gold: Language identification in the limit, in Information and control, Vol. 10, pp. 447–474 (1967).CrossRefGoogle Scholar
  2. 2.
    L.G. Valiant: A theory of the learnable, in Comm. ACM 27, (11), 1984, pp. 1134–1142.CrossRefGoogle Scholar
  3. 3.
    D. Haussler: Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework, in Artificial Intelligence 36, pp. 177–221, (1988).CrossRefGoogle Scholar
  4. 4.
    H. Hirsh: Polynomial-Time Learning with Version Space, in the proceedings of the 9th International Conference on Machine Learning, pp. 117–122, (1992).Google Scholar
  5. 5.
    R. Quinlan: Learning efficient classification procedures, in Machine Learning: an artificial intelligence approach, Michalski, Carbonell & Mitchell (eds.), Morgan Kaufmann, p. 463–482, (1983).Google Scholar
  6. 6.
    R. Quinlan: The effect of noise on concept learning, in Machine Learning: an artificial intelligence approach, Vol. II, Michalski, Carbonell & Mitchell (eds.), Morgan Kaufmann, p. 149–166, (1986).Google Scholar
  7. 7.
    S. Muggleton, C. Feng: Efficient Induction of Logic Programs, Proceedings of the First Conference on Algorithmic Learning Theory, Tokyo, Japan: Ohmasha. (1990).Google Scholar
  8. 8.
    T. Mitchell: Generalization as search, in Artificial Intelligence 18, pp. 203–226, (1982).CrossRefGoogle Scholar
  9. 9.
    A. Bundy, B. Silver, D. Plummer: An analytical comparison of some rulelearning programs, in Artificial Intelligence 27, (1985).Google Scholar
  10. 10.
    T. Mitchell: The need for Biases in Learning Generalizations, internal report Rutgers University, 1980, reprint in Readings in Machine Learning, Morgan Kaufman.Google Scholar
  11. 11.
    P. Utgoff: Shift of bias for inductive concept learning, in Machine Learning: an artificial intelligence approach, Vol. II, Michalski, Carbonell & Mitchell (eds.), Morgan Kaufmann, (1986).Google Scholar
  12. 12.
    J. Nicolas: Une représentation efficace pour les espaces des versions, in Proceedings of the Journées Francophones d'Apprentissage, (1993).Google Scholar
  13. 13.
    C. Carpineto: Trading off Consistency and Efficiency in Version-Space Induction, in the proceedings of the 9th International Conference on Machine Learning, pp. 43–48, (1992).Google Scholar
  14. 14.
    G. Birkhoff: Lattice theory, Third Edition, American Mathematical Society, Providence, RI (1967).Google Scholar
  15. 15.
    J.-G. Ganascia: An algebraic formalization of CHARADE, LAFORIA, Internal report, (1992).Google Scholar
  16. 16.
    J.-G. Ganascia: TDIS: an Algebraic Formalization, in the Proceedings of International Jointed Conference on Artificial Intelligence, (1993).Google Scholar
  17. 17.
    P. Clark, T. Niblett: The CN2 Induction Algorithm, in Machine Learning, 3, 1987, pp. 261–283.Google Scholar
  18. 18.
    C. Hempel: Aspects of Scientific Explanation and other Essays in the Philosophy of Science, The Free Press, A Division of Macmillan Publishing Co. Inc., New-York, (1965).Google Scholar
  19. 19.
    R. Wille: Knowledge Acquisition by methods of formal concept analysis, Technische hochschule Darmstadt, Fachbereich Mathematik, preprint N∘ 1238, (1989).Google Scholar
  20. 20.
    G. Grätzer: General Lattice Theory, Academic Press, New-York, (1978).Google Scholar
  21. 21.
    H. Rasiowa: An algebraic Approach to Non-Classical Logics, Studies in Logic and the Foundations of Mathematics, North-Holland, Amsterdam-London, (1974).Google Scholar
  22. 22.
    L. Henkin, D. Monk, A. Tarski: Cylindric Algebras, Studies in Logic and the Foundations of Mathematics, Vol. 64, North-Holland Publihing Company, Amsterdam, (1971).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Jean-Gabriel Ganascia
    • 1
  1. 1.LAFORIA - Institut Biaise PascalUniversité Pierre et Marie CURIEParis, CedexFrance

Personalised recommendations