Inference Policies
This work addresses the design of AI inference systems for domain-specific applications, but it is incremental as it builds on existing ideas without presenting new empirical results or benchmarks.
The paper explores the concept of inference policies tailored to specific problem domains, arguing that these policies need not adhere to general theories of rational inference, such as Bayesian reasoning, and may even lead to non-Bayesian procedures.
It is suggested that an AI inference system should reflect an inference policy that is tailored to the domain of problems to which it is applied -- and furthermore that an inference policy need not conform to any general theory of rational inference or induction. We note, for instance, that Bayesian reasoning about the probabilistic characteristics of an inference domain may result in the specification of an nonBayesian procedure for reasoning within the inference domain. In this paper, the idea of an inference policy is explored in some detail. To support this exploration, the characteristics of some standard and nonstandard inference policies are examined.