Uncertain Information Processing In Expert Systems
Uncertain Information Processing in Expert Systems systematically and critically examines probabilistic and rule-based (compositional, MYCIN-like) systems, the two most important families of expert systems dealing with uncertainty. The book features a detailed introduction to probabilistic systems (including methods using graphical models and methods of knowledge integration), an analysis of compositional systems based on algebraic considerations, an application of graphical models, and the Dempster-Shafer theory of evidence and its use in expert systems. The book will be useful to anyone working in artificial intelligence, statistical computing, symbolic logic, and expert systems.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Basic Mathematical Notions
Graphs and Probability
Decision Making Under Uncertainty
Local Computations with Probabilities on Graphical Structures
Knowledge Integration Methods
An Introduction to Compositional Systems
An Algebraic Analysis
A Probabilistic Analysis of Compositional Systems
The DempsterShafer Theory of Evidence and Its
Estimation of Probabilities and Structures
abelian group algorithm assume assumption axiom Bayesian belief functions Boolean bp assignment causal graph Chapter Clearly cliques of G collapsible combining functions complete compositional systems compute conditional distribution conditional independence conditional probability tables conditional weight system Consider consistent convex subgroup corresponding d-pairs d-potential d-space decision function decomposable defined Definition Dempster-Shafer theory Dempster's denote edges elementary conjunction Equation example expert systems finite focal element formula frame given global weight graph G Havranek hence implies input knowledge isomorphic joint probability distribution Lemma Let G log-linear models mapping Markov property maximal modus ponens MYCIN node nonextremal obtained optimal ordering possible potentials probabilistically sound probability theory Proof proposition PROSPECTOR question questionnaire random events random field random variate rule base running intersection property Section semigroup sequence Shannon entropy subsets system of cliques Theorem three-valued tion triangulated uniquely values vertex vertices We(p