Interpretable and Pedagogical Examples

Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate interpretability by (1) measuring the similarity of the teacher's emergent strategies to intuitive strategies in each domain and (2) conducting human experiments to evaluate how effective the teacher's strategies are at teaching humans. We show that the teacher network learns to select or generate interpretable, pedagogical examples to teach rule-based, probabilistic, boolean, and hierarchical concepts.

[1]  E. Rosch,et al.  Family resemblances: Studies in the internal structure of categories , 1975, Cognitive Psychology.

[2]  K. Holyoak,et al.  Induction of category distributions: a framework for classification learning. , 1984, Journal of experimental psychology. Learning, memory, and cognition.

[3]  John R. Anderson,et al.  The Adaptive Nature of Human Categorization , 1991 .

[4]  John R. Anderson,et al.  The Adaptive Nature of Human Categorization. , 1991 .

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

[6]  F. Ashby,et al.  Categorization as probability density estimation , 1995 .

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

[8]  Dana Angluin,et al.  Teachers, learners and black boxes , 1997, COLT '97.

[9]  Frank Stephan,et al.  Avoiding coding tricks by hyperrobust learning , 2002, Theor. Comput. Sci..

[10]  J. Tenenbaum,et al.  Word learning as Bayesian inference. , 2007, Psychological review.

[11]  T. Jaeger,et al.  Categorical Data Analysis: Away from ANOVAs (transformation or not) and towards Logit Mixed Models. , 2008, Journal of memory and language.

[12]  Noah D. Goodman,et al.  Teaching Games : Statistical Sampling Assumptions for Learning in Pedagogical Situations , 2008 .

[13]  Adam N. Sanborn,et al.  Categorization as nonparametric Bayesian density estimation , 2008 .

[14]  N. Chater,et al.  The probabilistic mind: prospects for Bayesian cognitive science , 2008 .

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

[16]  A. Gopnik,et al.  Children’s imitation of causal action sequences is influenced by statistical and pedagogical evidence , 2011, Cognition.

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

[18]  Michael C. Frank,et al.  Learning From Others , 2012, Perspectives on psychological science : a journal of the Association for Psychological Science.

[19]  Noah D. Goodman,et al.  A rational account of pedagogical reasoning: Teaching by, and learning from, examples , 2014, Cognitive Psychology.

[20]  Shimon Whiteson,et al.  Learning to Communicate with Deep Multi-Agent Reinforcement Learning , 2016, NIPS.

[21]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Rob Fergus,et al.  Learning Multiagent Communication with Backpropagation , 2016, NIPS.

[23]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[24]  José M. F. Moura,et al.  Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog , 2017, EMNLP.

[25]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[26]  Andrew Gordon Wilson,et al.  Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning , 2017 .

[27]  Adrian Weller,et al.  Challenges for Transparency , 2017, ArXiv.

[28]  Stefan Lee,et al.  Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[29]  Alexander Peysakhovich,et al.  Multi-Agent Cooperation and the Emergence of (Natural) Language , 2016, ICLR.

[30]  Pieter Abbeel,et al.  Emergence of Grounded Compositional Language in Multi-Agent Populations , 2017, AAAI.

[31]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[32]  Adrian Weller,et al.  Transparency: Motivations and Challenges , 2017, Explainable AI.