A complete approach to reasoning under uncertainty requires support for both identification of the appropriate hypothesis space and ranking hypotheses based on available evidence. We present a hybrid reasoning scheme which combines symbolic and numeric methods for uncertainty management to provide efficient and effective support for both of these tasks....
This report describes of current research in Artificial Intelligence at Oregon State University. The five areas of active research are ( a) intelligent aids for mechanical engineering design, (b) active experimentation as a method in machine learning, ( c) techniques for combining logic programming and assumption-based truth maintenance, ( d)...
A complete approach to uncertainty management requires support for interactive and incremental problem formulation, inference, hypothesis ranking, and decision making. In addition, computational models must allow for time and resource bounds. Current approaches to uncertainty management concentrate primarily on inference, provide little or no support for the larger issues in...
Reasoning about physical systems requites the integration of a range of knowledge and reasoning techniques. P. Hayes has named the enterprise of identifying and formalizing the common-sense knowledge people use for th.is task "naive physics." Qualitative Process theory by K. Forbus proposes a structure and some of the content of...
A Belief Net is a factored representation for a joint probability distribution over a set of variables. This factoring is made possible by the conditional independence relationships among variables made evident in the sparseness of the graphical level of the net. There is, however, another source of factoring available which...