An Inequality Paradigm for Probabilistic Knowledge (1986)
by Benjamin N. Grosof
Abstract:
We propose an inequality paradigm for probabilistic reasoning based on
a a logic of upper and lower bounds on conditional probabilities. We investigate
a family of probabilistic logics, generalizing the work of Nilsson. We develop
a variety of logical notions for probabilistic reasoning, including soundness;
completeness; and justification; and convergence: reduction of a theory
to a simpler logical class. We argue that a bounds view is especially useful
for describing the semantics of probabilistic knowledge representation and for
describing intermediate states of probabilistic inference and updating.
We show that the Dempter-Shafer theory of evidence is formally identical to
a special case of our generalized probabilistic logic. Our paradigm thus
incorporates both Bayesian "rule-based" approaches and avowedly non-Bayesian
"evidential" approaches such as MYCIN and Dempster-Shafer. We suggest how
to integrate the two "schools", and explore some possibilities for novel
synthesis of a variety of ideas in probabilistic reasoning.
Last update: 1-8-98
Up to Benjamin Grosof's Papers page
Up to Benjamin Grosof home page
[ IBM Research home page ][
IBM home page |
Order |
Search |
Contact IBM |
Help |
(C) |
(TM)
]