A Component-Model Approach to Determining What to Learn

Goal-Driven Learning

Volume

Papers from the 1994 AAAI Spring Symposium

Contents

Research in machine learning has typically addressed the problem of how and when to learn, and ignored the problem of formulating learning tasks in the first place. This paper addresses this issue in the context of the CASTLE system, that dynamically formulates learning tasks for a given situation. Our approach utilizes an explicit model of the decision-making process to pinpoint which system component should be improved. CASTLE can then focus the learning process on the issues involved in improving the performance of the particular component.