Algebraic versus probabilistic independence in decision theory

  • Authors:

  • S K M Wong;W Ziarko

  • Affiliations:

  • Department of Computer Science, University of Regina, Regina, Saskatchewan, Canada S4S 0A2;Department of Computer Science, University of Regina, Regina, Saskatchewan, Canada S4S 0A2

  • Venue:
  • ISMIS '86 Proceedings of the ACM SIGART international symposium on Methodologies for intelligent systems
  • Year:
  • 1986

Quantified Score

Hi-index 0.00

Visualization

Abstract

The study of independence (dependence) between the condition and decision attributes is an important issue in decision theory. Most important applications in artificial intelligence are non-deterministic. It is shown that algebraic dependence is not adequate in these situations, and probabilistic independence provides a correct measure of information uncertainty for expert system design.