Coherence, Explanation, and Bayesian Networks

Abstract

This paper discusses the relevance of coherence to deciding between competing explanations. It provides a basic definition of coherence in probabilistic terms, which yields a coherence measure and can easily be extended from the coherence of two beliefs to the coherence of n beliefs. Using this definition, the coherence of a set of beliefs can be obtained by making simple extensions to a Bayesian network. The basic definition suggests a strategy for revising beliefs since a decision to reject a belief can be based on maximising the coherence of the remaining beliefs. It is also argued that coherence can provide a suitable approach for inference to the best explanation.