Advertisement

PAC-Learning and Occam’s Razor

  • Uwe Schöning
  • Randall Pruim

Abstract

Many (algorithmic) learning theories have been developed. The one which is now most often considered originated with L. Valiant (1984) and is called PAC-learning. In this chapter we show an interesting connection between PAC-learning and the principal known as “Occam’s Razor.”

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. L.G. Valiant: A theory of the learnable, Communications of the ACM 27 (1984), 1134–1142.zbMATHCrossRefGoogle Scholar
  2. A. Blumer, A. Ehrenfeucht, D. Haussler, M.K. Warmuth: Occam’s Razor, Information Processing Letters 24 (1987), 377–380.MathSciNetzbMATHCrossRefGoogle Scholar
  3. A. Blumer, A. Ehrenfeucht, D. Haussler, M.K. Warmuth: Learnability and the Vapnik-Chervonenkis dimension, Journal of the ACM 36 (1989), 929–965.MathSciNetzbMATHCrossRefGoogle Scholar
  4. R. Board, L. Pitt: On the necessity of Occam algorithms, Proceedings of the 22nd Symposium on Theory of Computing, ACM, 1990, 54-63.Google Scholar
  5. D. Angluin: Computational learning theory: survey and selected bibliography, Proceedings of the 24th Symposium on Theory of Computing, ACM, 1992, 351-369.Google Scholar
  6. B. Natarajan: Machine Learning, Morgan Kaufmann, 1991.Google Scholar
  7. M. Anthony, N. Biggs: Computational Learning Theory, Cambridge University Press, 1992.Google Scholar
  8. M. Li, P. Vitanyi: An Introduction to Kolmogorov Complexity and its Applications j 2nd edition, Springer, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Uwe Schöning
    • 1
  • Randall Pruim
    • 2
  1. 1.Abt. Theoretische InformatikUniversität UlmUlmGermany
  2. 2.Dept. of Mathematics and StatisticsCalvin CollegeGrand RapidsUSA

Personalised recommendations