1 Problems Facing Theory

Current theory-guided learning systems are innexible, in that they are committed to performing one particular class of theory corrections ; this is problematic because in some cases special-purpose theory-guided learning systems can dramatically outperform general-purpose ones. To address this problem , we describe a new system in which theory-guided learning is separated into two phases. The rst phase is \theory intrepre-tation", in which the initial theory is translated into an explicit description of the bias for an inductive learning system; we introduce antecedent description grammars as a language for explicitly representing this bias. The second phase is \grammatically biased learning", in which this bias is used to search for a hypothesis. We demonstrate empirically that this approach leads to a exible learning system which can, by use of suitable translators , emulate several useful learning systems; we also argue that this architecture makes it easier for a user unfamiliar with the details of the learning system to predict the impact that an initial theory will have on learning.