How Do Humans Teach: On Curriculum Learning and Teaching Dimension

Abstract

We study the empirical strategies that humans follow as they teach a target concept with a simple 1D threshold to a robot.1 Previous studies of computational teach-ing, particularly the teaching dimension model and the curriculum learning prin-ciple, offer contradictory predictions on what optimal strategy the teacher should follow in this teaching task. We show through behavioral studies that humans em-ploy three distinct teaching strategies, one of which is consistent with the curricu-lum learning principle, and propose a novel theoretical framework as a potential explanation for this strategy. This framework, which assumes a teaching goal of minimizing the learner’s expected generalization error at each iteration, extends the standard teaching dimension model and offers a theoretical justification for curriculum learning. 1