A Method for Multistrategy Task-Adaptive Learning Based on Plausible Justifications

Abstract

Multistrategy task-adaptive learning (MTL) comprises a class of methods in which the learner determines by itself which strategy or combination of strategies is most appropriate for a given learning task defined by the learner's goal, the learner's background knowledge (BK) and the input to the learning process. The paper presents a MTL method which is based on building a plausible justification that the learner's input is a consequence of its BK. The method assumes a general learning goal of deriving any useful knowledge from a given input and integrates dynamically a whole range of learning strategies. It also behaves as a single-strategy method when the relationship between the input and the BK satisfies the requirements of the single-strategy method, and the general learning goal of the MTL method is specialized to the goal of the single-strategy method. Joint appointment with the Research Institute for Informatics, 71316, Bd.Miciurin 8-10, Bucharest 1, Romania