A maximum entropy approach to nonmonotonic reasoning

  • Authors:
  • Moisés Goldszmidt;Paul Morris;Judea Pearl

  • Affiliations:
  • Cognitive Systems Lab., University of California, Los Angeles, CA;Intellicorp, Mountain View, CA;Cognitive Systems Lab., University of California, Los Angeles, CA

  • Venue:
  • AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1
  • Year:
  • 1990

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes a probabilistic approach to nonmonotonic reasoning which combines the principle of infinitesimal probabilities with that of maximum entropy, and which sanctions inferences similar to those produced by the principle of minimizing abnormalities. The paper provides a precise formalization of the consequences entailed by a defeasible knowledge base, develops the computational machinery necessary for deriving these consequences, and compares the behavior of the maximum entropy approach to those of Ɛ-semantics ([Pearl 89a]) and rational closure ([Lehmann 89]).