Teaching a smart learner

We introduce a formal model of teaching in which the teacher is tailored to a particular learner, yet the teaching protocol is designed so that no collusion is possible. Not surprisingly, such a model remedies the nonintuitive aspects of other models in which the teacher must successfully teach any consistent learner. We prove that any class that can be exactly identified by a polynomial-time algorithm with access to a very rich set of examplebased queries is teachable by a computationally unbounded teacher and a polynomial-time learner. In addition, we present other general results relating this model of teaching to various previous results. We also consider the problem of designing teacher/learner pairs in which both the teacher and learner are polynomial-time algorithms and describe teacher/learner pairs for the classes of decision lists and Horn sentences.

[1]  Silvio Micali,et al.  The Knowledge Complexity of Interactive Proof Systems , 1989, SIAM J. Comput..

[2]  D. Angluin.  Queries and Concept Learning , 1988 .

[3]  Lisa Hellerstein,et al.  Read-thrice DNF is hard to learn with membership and equivalence queries , 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

[4]  Rusins Freivalds,et al.  On the Power of Inductive Inference from Good Examples , 1993, Theor. Comput. Sci..

[5]  Ronald L. Rivest,et al.  Learning Binary Relations and Total Orders , 1993, SIAM J. Comput..

[6]  Manfred K. Warmuth,et al.  Learning nested differences of intersection-closed concept classes , 2004, Machine Learning.

[7]  Tom M. Mitchell,et al.  Version Spaces: A Candidate Elimination Approach to Rule Learning , 1977, IJCAI.

[8]  N. Littlestone.  Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm , 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[9]  Manfred K. Warmuth,et al.  Learning Nested Differences of Intersection-Closed Concept Classes , 1989, COLT '89.

[10]  John Shawe-Taylor,et al.  On exact specification by examples , 1992, COLT '92.

[11]  Thomas R. Hancock,et al.  Identifying μ-formula decision trees with queries , 1990, COLT '90.

[12]  Balas K. Natarajan,et al.  On learning Boolean functions , 1987, STOC.

[13]  Ronald L. Rivest,et al.  Learning decision lists , 2004, Machine Learning.

[14]  Simon Kasif,et al.  Learning with a Helpful Teacher , 1991, IJCAI.

[15]  Andrew Tomkins,et al.  A computational model of teaching , 1992, COLT '92.

[16]  Carl Smith,et al.  Testing Geometric Objects , 1994, Comput. Geom..

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

[18]  Sally Floyd,et al.  Space-bounded learning and the Vapnik-Chervonenkis dimension , 1989, COLT '89.

[19]  Kathleen Romanik,et al.  Approximate testing and learnability , 1992, COLT '92.