How Do Humans Teach: On Curriculum Learning and Teaching Dimension

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 teaching, particularly the teaching dimension model and the curriculum learning principle, offer contradictory predictions on what optimal strategy the teacher should follow in this teaching task. We show through behavioral studies that humans employ three distinct teaching strategies, one of which is consistent with the curriculum 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]  William M. Smith,et al.  A Study of Thinking , 1956 .

[2]  M. Kearns,et al.  On the complexity of teaching , 1991, COLT '91.

[3]  Tibor Hegedűs,et al.  Generalized teaching dimensions and the query complexity of learning , 1995, Annual Conference Computational Learning Theory.

[4]  Sally A. Goldman,et al.  Teaching a Smarter Learner , 1996, J. Comput. Syst. Sci..

[5]  Dana Angluin,et al.  Queries revisited , 2001, Theoretical Computer Science.

[6]  James L. McClelland,et al.  Success and failure in teaching the [r]-[l] contrast to Japanese adults: Tests of a Hebbian model of plasticity and stabilization in spoken language perception , 2002, Cognitive, affective & behavioral neuroscience.

[7]  Herbert A. David,et al.  Order Statistics, Third Edition , 2003, Wiley Series in Probability and Statistics.

[8]  Thomas Zeugmann,et al.  Teaching Randomized Learners , 2006, COLT.

[9]  Steve Hanneke,et al.  Teaching Dimension and the Complexity of Active Learning , 2007, COLT.

[10]  Gert Storms,et al.  Word associations: Network and semantic properties , 2008, Behavior research methods.

[11]  Gert Storms,et al.  Word associations: Norms for 1,424 Dutch words in a continuous task , 2008, Behavior research methods.

[12]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[13]  Thomas Zeugmann,et al.  Recent Developments in Algorithmic Teaching , 2009, LATA.

[14]  Ayumi Shinohara,et al.  Complexity of Teaching by a Restricted Number of Examples , 2009, COLT.

[15]  Daphne Koller,et al.  Self-Paced Learning for Latent Variable Models , 2010, NIPS.

[16]  Joshua P. Salmon,et al.  Norms for two types of manipulability (graspability and functional usage), familiarity, and age of acquisition for 320 photographs of objects , 2010, Behavior research methods.

[17]  Sandra Zilles,et al.  Models of Cooperative Teaching and Learning , 2011, J. Mach. Learn. Res..

[18]  Yong Jae Lee,et al.  Learning the easy things first: Self-paced visual category discovery , 2011, CVPR 2011.