Learning Convex Bodies under uniform distribution

Walter Kern

Research output: Contribution to journalArticleAcademicpeer-review

111 Downloads (Pure)

Abstract

We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.
Original languageUndefined
Pages (from-to)35-39
Number of pages5
JournalInformation processing letters
Volume0
Issue number43
DOIs
Publication statusPublished - 1992

Keywords

  • Theory of computation
  • convex bodies
  • METIS-140518
  • uniform distribution
  • IR-29884
  • learning by example

Cite this