PAC Learning of Concept Classes Through the Boundaries of Their Items

  title={PAC Learning of Concept Classes Through the Boundaries of Their Items},
  author={Bruno Apolloni and S. Chiaravalli},
  journal={Theor. Comput. Sci.},
We present a new perspective for investigating the Probably Approximate Correct (PAC) learnability of classes of concepts. We focus on special sets of points for characterizing the concepts within their class. This gives rise to a general notion of boundary of a concept, which holds even in discrete spaces, and to a special probability measuring technique. This technique is applied (i) to narrow the gap between the minimum and maximum sample sizes necessary to learn under a more stringent… CONTINUE READING
10 Citations
6 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 10 extracted citations


Publications referenced by this paper.
Showing 1-6 of 6 references

Chervonenkis , On the uniform convergence of relative frequencies of events to their probabilities

  • A. Ya. V. V. Vapnik
  • Estimation of dependences based on empirical data
  • 1982

Some special VapnickChervonenkis classes , Discr

  • R. M. Dudley
  • Th . Prob . and its Appl .
  • 1971

Non parametric estimation II . Statistical equivalent blocks and tolerance regionsThe continuous case

  • J. W. Tukey
  • Annals of Math . Stat .

Similar Papers

Loading similar papers…