On learning from queries and counterexamples in the presence of noise

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.

Original languageEnglish
Pages (from-to)279-284
Number of pages6
JournalInformation Processing Letters
Volume37
Issue number5
DOIs
Publication statusPublished - 1991 Mar 14
Externally publishedYes

    Fingerprint

Keywords

  • analysis of algorithms
  • Concept learning
  • formal languages
  • noise
  • queries
  • random sampling

ASJC Scopus subject areas

  • Computational Theory and Mathematics

Cite this