Uncertainty in Artificial Intelligence 3: (Machine Intelligence & Pattern Recognition)

Being a subject of much controversy in Artificial Intelligence, there are still many open fundamental issues in the area of uncertain reasoning. This third volume presents new research results, representing significant progress in a number of issues. Because representation and reasoning under uncertainty are still poorly understood, and because implementation choices and tradeoffs are best understood in the context of specific applications, most of the papers address multiple issues in uncertain reasoning. They are divided into four categories: Interpretation and comparison of uncertainty calculi; Representation and computation in Bayesian inference; Structure and control for systems reasoning under uncertainty; and Learning and explanation.

Table of Contents:
Interpretation and Comparison. An Algorithm for Computing Probabilistic Propositions (G.F. Cooper). Higher Order Probabilities (H.E. Kyburg). Nilsson's Probabilistic Entailment Extended to Dempster-Shafer Theory (M. McLeish). Towards Solving the Multiple Extension Problem: Combining Defaults and Probability (E. Neufeld, D. Poole). Satisfaction of Assumptions is a Weak Predictor of Performance (B.P. Wise). Evaluation of Uncertain Inference Models III: The Role of Tuning (B.P. Wise et al.). Can Evidence be Combined in the Dempster-Shafer Theory (J. Yen). Representation and Computation in Bayesian Inference. Bayesian Inference in Model-Based Machine Vision (T.O. Binford, T.S. Levitt, W.B. Mann). Computing Belief Commitments Using Tensor Products (L.B. Booker, N. Hota, G. Hemphill). Decision Tree Induction Systems: A Bayesian Analysis (W.L. Buntine). Bayesian Belief Network Inference Using Stimulation (H.L. Chin, G.F. Cooper). A Bayesian Perspective on Confidence (D. Heckerman, H. Jimison). Some Practical Issues in Constructing Belief Networks (M. Henrion). The Recovery of Causal Poly-Trees from Statistical Data (G. Rebane, J. Pearl). A Heuristic Bayesian Approach to Knowledge Acquisition: Application to the Analysis of Tissue-Type Plasminogen Activator (R.D. Shachter et al.). Advantages and a Limitation of Using LEG Nets in a Real-Time Problem (T.B. Slack). A Unified Approach to Impression and Sensitivity of Beliefs in Expert Systems (D.J. Spiegelhalter). Structuring Causal Tree Models with Continuous Variables (L. Xu, J. Pearl). Structure and Control. Using the Dempster-Shafer Scheme in a Mixed-Initiative Expert System Shell (G. Biswas, T.S. Anand). T-norm Based Reasoning in Situation Assessment Applications (P.S. Bonissone, N.C. Wood). Steps Towards Programs that Manage Uncertainty (P.R. Cohen). A Hybrid Approach to Reasoning Under Uncertainty (B. D'Ambrosio). Estimation Procedures for Robust Sensor Control (G. Hager, M. Mintz). Reasoning About Beliefs and Actions Under Computational Resource Constraints (E.J. Horvitz). Efficient Inference on Generalized Fault Diagrams (R.D. Shachter, L.J. Bertrand). Implementing Evidential Reasoning in Expert Systems (J. Yen). Learning and Explanation. The Automatic Training of Rule Bases that use Numerical Uncertainty Representations (R.A. Caruana). Modifiable Combining Functions (P.R. Cohen, G. Shafer, P.P. Shenoy). The Inductive Logic of Information Systems (N. Dalkey). Explanation of Probabilistic Inference (C. Elsaesser). Theory-Based Inductive Learning: An Integration of Symbolic and Quantitative Methods (S. Star).