Advertisement

Learnability of Enumerable Classes of Recursive Functions from “Typical” Examples

  • Jochen Nessel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1720)

Abstract

The paper investigates whether it is possible to learn every enumerable classes of recursive functions from “typical” examples. “Typical” means, there is a computable family of finite sets, such that for each function in the class there is one set of examples that can be used in any suitable hypothesis space for this class of functions. As it will turn out, there are enumerable classes of recursive functions that are not learnable from “typical” examples. The learnable classes are characterized.

The results are proved within an abstract model of learning from examples, introduced by Freivalds, Kinber and Wiehagen. Finally, the results are interpreted and possible connections of this theoretical work to the situation in real life classrooms are pointed out.

Keywords

Initial Segment Recursive Function Target Class Hypothesis Space Inference Machine 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jain, S., Lange, S., Nessel, J. (1997), Learning of r.e. Languages from Good Examples, in Li, Maruoka, Eds., Eighth International Workshop on Algorithmic Learning Theory, 32–47, Lecture Notes in Artificial Intelligence 1316, Springer Verlag.Google Scholar
  2. 2.
    Freivalds, R., Kinber, E.B., Wiehagen, R. (1993), On the power of inductive inference from good examples. Theoretical Computer Science 110, 131–144.zbMATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Gold, E.M. (1967), Language identification in the limit. Information and Control 10, 447–474.CrossRefzbMATHGoogle Scholar
  4. 4.
    Goldman, S.A., Mathias, H.D. (1996), Teaching a smarter learner. Journal of Computer and System Sciences 52, 255–267.CrossRefMathSciNetGoogle Scholar
  5. 5.
    Kummer, M. (1995), A Learning-Theoretic Characterization of Classes of Recursive Functions, Information Processing Letters 54, 205–211.zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Lange, S., Nessel, J., Wiehagen, R. (1998), Learning recursive languages from good examples, Annals of Mathematics and Artificial Intelligence 23, 27–52.zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Lange, S., Zeugmann, T. (1993), Language Learning in Dependence on the Space of Hypotheses, Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, 127–136, ACM Press.Google Scholar
  8. 8.
    Lange, S., Zeugmann, T. (1993), Learning recursive languages with bounded mindchanges, International Journal of Foundations of Computer Science 2, 157–178.CrossRefMathSciNetGoogle Scholar
  9. 9.
    Marchenkov, S. S. (1972), The computable enumerations of families of recursive functions, Algebra i Logika 11, 588–607; English Translation Algebra and Logic 15, 128–141, 1972.MathSciNetGoogle Scholar
  10. 10.
    Rogers, H. Jr. (1987), Theory of Recursive Functions and Effective Computability, MIT Press, Cambridge, Massachusetts.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Jochen Nessel
    • 1
  1. 1.University of KaiserslauternKaiserslauternGermany

Personalised recommendations