Absolute versus probabilistic classification in a logical setting
No Thumbnail Available
Date
2006-03-22T01:23:33Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Given a set W of logical structures, or possible worlds, a set of logical formulas called possible data and a logical formula phi, we consider the classification problem of determining in the limit and almost always correctly whether a possible world M in W satisfies phi, from a complete enumeration of the possible data that are true in M. One interpretation of almost always correctly is that the classification might be wrong on a set of possible worlds of measure 0, with respect to some natural probability distribution over the set of possible worlds. Another interpretation is that the classifier is only required to classify a set W' of possible worlds of measure 1, without having to produce any claim in the limit on the truth of phi in the members of W which are not in W'. We compare these notions with absolute classification of W with respect to a formula that is almost always equivalent to phi in W, hence investigate whether the set of possible worlds on which the classification is correct is definable. We mainly work with the probability distribution that corresponds to the standard measure on the Cantor space, but we also consider an alternative probability distribution proposed by Solomonoff and contrast it with the former. Finally, in the spirit of the kind of computations considered in Logic programming, we address the issue of computing almost correctly in the limit witnesses to leading existentially quantified variables in existential formulas.