A Model of Interactive Teaching

Abstract

Previous teaching models in the learning theory community have been batch models. That is, in these models the teacher has generated a single set of helpful examples to present to the learner. In this paper we present an interactive model in which the learner has the ability to ask queries as in the query learning model of Angluin. We show that this model is at least as powerful as previous teaching models. We also show that anything learnable with queries, even by a randomized learner, is teachable in our model. In all previous teaching models, all classes shown to be teachable are known to be efficiently learnable. An important concept class that is not known to be learnable is DNF formulas. We demonstrate the power of our approach by providing a deterministic teacher and learner for the class of DNF formulas. The learner makes only equivalence queries and all hypotheses are also DNF formulas. ] 1997 Academic Press

Eliciting good teaching from humans for machine learners

“…A helpful teacher can significantly improve the learning rate of a ML algorithm, as shown in the field of Algorithmic Teaching [3,29,15]. This field studies the teaching problem, that is, producing a set of labeled examples based on a known target concept.…”

Teaching Randomized Learners

“…Freivalds et al [8] and Jain et al [13]). Jackson and Tomkins [12] as well as Goldman and Mathias [10] and Mathias [15] defined models of teacher/learner pairs. In their models, a kind of adversary disturbing the teaching process is necessary to avoid collusion between the teacher and the learner.…”

Recent Developments in Algorithmic Teaching

“…Jackson and Tomkins [22] as well as Goldman and Mathias [18,27] defined models of teacher/learner pairs where teachers and learners are constructed explicitly. In all these models, some kind of adversary disturbing the teaching process is necessary to avoid collusion between the teacher and the learner.…”