Learning by Smooth Simultaneous Estimation of the Error of Hypotheses Conference Paper uri icon

abstract

  • We consider the Probably Approximately Correct (PAC) model of 'learning,' introduced in [1]. Given data that consists of labeled samples, the problem is to select a 'hypothesis' (a function) that will accurately label new samples. We investigated an approach, different from the usual one, that first estimates the error of each candidate hypothesis and then selects the hypothesis with the least estimated error.

name of conference

  • 1992 American Control Conference

published proceedings

  • 1992 American Control Conference

author list (cited authors)

  • Buescher, K. L., & Kumar, P. R.

citation count

  • 0

complete list of authors

  • Buescher, Kevin L||Kumar, PR

publication date

  • June 1992