Nonmonotonic reasoning, preferential models and cumulative logics
Artificial Intelligence
Beyond inversion of resolution
Proceedings of the seventh international conference (1990) on Machine learning
Nonmonotonic inference based on expectations
Artificial Intelligence
Theory refinement combining analytical and empirical methods
Artificial Intelligence
Revisions of knowledge systems using epistemic entrenchment
TARK '88 Proceedings of the 2nd conference on Theoretical aspects of reasoning about knowledge
Horn complements: towards horn-to-horn belief revision
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Hi-index | 0.00 |
Belief change is concerned with modelling the way in which a rational reasoner maintains its beliefs as it acquires new information. Of particular interest is the way in which new beliefs are acquired and determined and old beliefs are retained or discarded. A parallel can be drawn to symbolic machine learning approaches where examples to be categorised are presented to the learning system and a theory is subsequently derived, usually over a number of iterations. It is therefore not surprising that the term 'theory revision' is used to describe this process [Ourston and Mooney, 1994]. Viewing a machine learning system as a rational reasoner allows us to begin seeing these seemingly disparate mechanisms in a similar light. In this paper we are concerned with characterising the well known inverse resolution operations [Muggleton, 1987; 1992] (and more recently, inverse entailment [Muggleton, 1995]) as AGM-style belief change operations. In particular, our account is based on the abductive expansion operation [Pagnucco et al., 1994; Pagnucco, 1996] and characterised by using the notion of epistemic entrenchment [Gärdenfors and Makinson, 1988] extended for this operation. This work provides a basis for reconciling work in symbolic machine learning and belief revision. Moreover, it allows machine learning techniques to be understood as forms of nonmonotonic reasoning.