Learning Regular Languages from Positive Evidence

Abstract

Children face an enormously difficult task in learning their native language. It is widely believed that they do not receive or make little use of negative evidence (Marcus, 1993) and yet it has been proven that many classes of languages less powerful than natural languages cannot be learned in the absence of negative evidence (Gold, 1964). In this paper we present an approach to learning good approximations to members of one such class of languages, the regular languages, based on positive evidence alone.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1998
Accession Number
ADA459428

Entities

People

  • Laura Firoiu
  • Paul R. Cohen
  • Tim Oates

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Automata
  • Computer Science
  • Computers
  • Computing Devices
  • Context Free Grammars
  • Grammars
  • Language
  • Learning
  • National Security
  • Natural Languages
  • Neural Networks
  • Probability
  • Probability Distributions
  • Recurrent Neural Networks
  • Symbols

Fields of Study

  • Computer science

Readers

  • STEM Education
  • Theoretical Analysis.