Formal Learning Theory in Context

Abstract

Publisher Summary Formal learning theory has a potential descriptive role in characterizing inductive practice. It does not essentially resolve the matter, but facilitates the articulation of the issue, preparing the way for subsequent clarification. The formal learning theory connects the classes of inductive strategies to the empirical problems for which they are adapted. This chapter reviews the formal learning theory and compares it to the statistical theory of confidence intervals. The theory of confidence intervals shares with the formal learning theory the goal of revealing a hidden reality on the basis of data that do not deductively imply the correct answer. The formal learning theory helps to evaluate policies for accepting hypotheses. It does not designate a uniquely best strategy, but seems relevant to the orderly adoption of hypotheses. Essentially, the formal learning theory justifies the choice of hypothesis by situating it in a strategy with good long-term prospects.