Representing Knowledge and Evidence for Decision

Abstract

Our decisions reflect uncertainty in various ways. We take account of the uncertainty embodied in the roll of the die; we less often take account of the uncertainty of our belief that the die is fair. We need to take account of both uncertain knowledge and our knowledge of uncertainty. Evidence itself has been regarded as uncertain. We argue that pointvalued probabilities are a poor representation of uncertainty; that we need not be concerned with uncertain evidence; that interval-valued probabilities that result from knowledge of convex sets of distribution functions in reference classes (properly) include Shafer's mass functions as a special case; that these probabilities yield a plausible non-monotonic form of inference (uncertain inference, inductive inference, statistical inference); and finally that this framework provides a very nearly classical decision theory -- so far as it goes. It is unclear how global the principles (such as minimax) that go beyond the principle of maximizing expected utility are. Artificial Intelligence, Data Fusion, evidence, uncertainty, decision non-monotonicity, knowledge representation, expert systems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1986
Accession Number
ADA250616

Entities

People

  • Henry E. Kyburg

Organizations

  • University of Rochester

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Algebra
  • Artificial Intelligence
  • Bayesian Networks
  • Convex Sets
  • Data Science
  • Decision Theory
  • Expert Systems
  • Information Science
  • Intervals
  • Mathematics
  • New York
  • Numbers
  • Probability
  • Statistical Analysis
  • Statistical Inference
  • Statistics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Artificial Intelligence

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms