Learning list concepts through program induction

Humans master complex systems of interrelated concepts like mathematics and natural language. Previous work suggests learning these systems relies on iteratively and directly revising a language-like conceptual representation. We introduce and assess a novel concept learning paradigm called Martha’s Magical Machines that captures complex relationships between concepts. We model human concept learning in this paradigm as a search in the space of term rewriting systems, previously developed as an abstract model of computation. Our model accurately predicts that participants learn some transformations more easily than others and that they learn harder concepts more easily using a bootstrapping curriculum focused on their compositional parts. Our results suggest that term rewriting systems may be a useful model of human conceptual representations.

[1]  Ned Block,et al.  Advertisement for a Semantics for Psychology , 1987 .

[2]  William M. Smith,et al.  A Study of Thinking , 1956 .

[3]  Douglas B. Lenat,et al.  EtmlSI O : A Program That Learns New Heuristics and Domain Concepts The Nature of Heuristics III : Program Design and Results , 2005 .

[4]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[5]  G. Murphy,et al.  The Big Book of Concepts , 2002 .

[6]  Sumit Gulwani,et al.  Program Synthesis , 2014, Software Systems Safety.

[7]  Ute Schmid,et al.  Inductive Synthesis of Functional Programs: An Explanation Based Generalization Approach , 2006, J. Mach. Learn. Res..

[8]  S. Laurence,et al.  The Conceptual Mind: New Directions in the Study of Concepts , 2015 .

[9]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[10]  Karin Ackermann,et al.  Categories and Concepts , 2003, Job 28. Cognition in Context.

[11]  M. R. K. Krishna Rao.  Inductive Inference of Term Rewriting Systems from Positive Data , 2004, ALT.

[12]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[13]  S. Carey.  The Origin of Concepts , 2000 .

[14]  Douglas B. Lenat,et al.  EURISKO: A Program That Learns New Heuristics and Domain Concepts , 1983, Artif. Intell..

[15]  William M. Smith,et al.  A Study of Thinking , 1956 .

[16]  Noah D. Goodman,et al.  The logical primitives of thought: Empirical foundations for compositional cognitive models. , 2016, Psychological review.

[17]  Pierre Flener,et al.  An introduction to inductive programming , 2008, Artificial Intelligence Review.

[18]  Joshua B. Tenenbaum,et al.  Bootstrap Learning via Modular Concept Discovery , 2013, IJCAI.

[19]  Steven Piantadosi,et al.  The computational origin of representation and conceptual change , 2016 .

[20]  Thomas L. Griffiths,et al.  A Rational Analysis of Rule-Based Concept Learning , 2008, Cogn. Sci..

[21]  C. Cordell Green,et al.  What Is Program Synthesis? , 1985, J. Autom. Reason..

[22]  Gerald J. Sussman,et al.  A Computational Model of Skill Acquisition , 1973 .

[23]  Allen Newell,et al.  Report on a general problem-solving program , 1959, IFIP Congress.

[24]  S. Laurence,et al.  Concepts: Core Readings , 1999 .

[25]  Noah D. Goodman,et al.  Bootstrapping in a language of thought: A formal model of numerical concept learning , 2012, Cognition.

[26]  D. McDermott.  LANGUAGE OF THOUGHT , 2012 .

[27]  Enno Ohlebusch,et al.  Term Rewriting Systems , 2002 .

[28]  Noah D. Goodman,et al.  Theory learning as stochastic search in the language of thought , 2012 .