Complexity dimensions and learnability

  • S. H. Nienhuys-Cheng
  • M. Polman
Position Papers Learnability
Part of the Lecture Notes in Computer Science book series (LNCS, volume 667)


In a discussion of the Vapnik Chervonenkis (VC) dimension ([7]), which is closely related to the learnability of concept classes in Valiant's PAC-model ([6]), we will give an algorithm to compute it. Furthermore, we will take Natarajan's equivalent dimension for well-ordered classes into a more general scheme, by showing that these well-ordered classes happen to satisfy some general condition, which makes it possible to construct for a class a number of equivalent dimensions. We will give this condition, as well as a relatively efficient algorithm for the calculation of one such dimension for well-ordered classes.


  1. 1.
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.: Learnability and the Vapnik-Chervonenkis Dimension. Journal of the Association for Computing Machinery 36 No. 4 (1989) 929–965Google Scholar
  2. 2.
    Natarajan, B.: On Learning Boolean Functions. Proceedings of the 19th Annual ACM Symposium on Theory of Computation 269–304Google Scholar
  3. 3.
    Natarajan, B.: Machine Learning, a Theoretical Approach. Morgan Kaufman Publishers, Inc (1991)Google Scholar
  4. 4.
    Nienhuys-Cheng, S.H., Polman, M.: Complexity Dimensions and Learnability. Research Report EUR-CS-92-06 (1992)Google Scholar
  5. 5.
    Polman, M., Nienhuys-Cheng, S.H.: Some Topics Related to PAC-Learning. Proceedings of CSN'92, Utrecht, Netherlands, (nov. 1992)Google Scholar
  6. 6.
    Valiant, L.G.: A theory of the learnable. Communications of the ACM 27 No. 11 (1984) 1134–1142Google Scholar
  7. 7.
    Vapnik, V., and Chervonenkis, A.: On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications 16 No. 2 (1971) 264–280Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • S. H. Nienhuys-Cheng
    • 1
  • M. Polman
    • 1
  1. 1.Dept. of Computer ScienceErasmus University of RotterdamThe Netherlands

Personalised recommendations