The concept of inductive bias can be broken down into the underlying assumptions of the domain, the particular implementation choices that restrict or order the space of hypotheses considered by the learning program (the bias choices), and the inductive policy that links the two. We define inductive policy as the strategy used to make bias choices based on the underlying assumptions. Inductive policy decisions involve addressing trade offs with respect to different bias choices. Without addressing these trade offs, bias choices will be made arbitrarily. From the standpoint of inductive policy, we discuss two issues not addressed much in the machine learning literature. First we discuss batch learning with a strict time constraint, and present an initial study with respect to trading off predictive accuracy for speed of learning. Next we discuss the issue of learning in a domain where different types of errors have different associated costs (risks). We show that by using different inductive policies accuracy can be traded off for safety. We also show how the value for the latter trade off can be represented explicitly in a system that adjusts bias choices with respect to a particular inductive policy.
© Copyright 2022 Foster Provost. All Rights Reserved.