Intelligible Artificial Intelligence

Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. In order to trust their behavior, we must make it intelligible --- either by using inherently interpretable models or by developing methods for explaining otherwise overwhelmingly complex decisions by local approximation, vocabulary alignment, and interactive dialog.

[1]  H. Grice.  Logic and conversation , 1975 .

[2]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[3]  William R. Swartout,et al.  XPLAIN: A System for Creating and Explaining Expert Consulting Programs , 1983, Artif. Intell..

[4]  Albert T. Corbett,et al.  Intelligent Tutoring Systems , 1985, Science.

[5]  D. Hilton.  Conversational processes and causal explanation. , 1990 .

[6]  Derek J. Koehler,et al.  Explanation, imagination, and confidence in judgment. , 1991, Psychological bulletin.

[7]  S. Sloman.  Explanatory Coherence and the Induction of Properties , 1997 .

[8]  Joseph Y. Halpern,et al.  Causes and explanations: A structural-model approach , 2000 .

[9]  T. Lombrozo,et al.  Simplicity and probability in causal explanation , 2007, Cognitive Psychology.

[10]  D. Kahneman.  Thinking, Fast and Slow , 2011 .

[11]  Alexis Papadimitriou,et al.  A generalized taxonomy of explanations styles for traditional and social recommender systems , 2012, Data Mining and Knowledge Discovery.

[12]  Johannes Gehrke,et al.  Intelligible models for classification and regression , 2012, KDD.

[13]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[14]  Ryan Calo.  The Case for a Federal Robotics Commission , 2014 .

[15]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[16]  Weng-Keen Wong,et al.  Principles of Explanatory Debugging to Personalize Interactive Machine Learning , 2015, IUI.

[17]  Ashish Kapoor,et al.  FeatureInsight: Visual support for error-driven feature ideation in text classification , 2015, 2015 IEEE Conference on Visual Analytics Science and Technology (VAST).

[18]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[19]  Johannes Gehrke,et al.  Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission , 2015, KDD.

[20]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[21]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  John Seely Brown,et al.  Intelligent Tutoring Systems , 2016, Lecture Notes in Computer Science.

[23]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[24]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[25]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[26]  Trevor Darrell,et al.  Generating Visual Explanations , 2016, ECCV.

[27]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[28]  Jure Leskovec,et al.  Interpretable & Explorable Approximations of Black Box Models , 2017, ArXiv.

[29]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

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

[31]  Bolei Zhou,et al.  Network Dissection: Quantifying Interpretability of Deep Visual Representations , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Maria Fox,et al.  Explainable Planning , 2017, ArXiv.

[33]  Thomas G. Dietterich.  Steps Toward Robust Artificial Intelligence , 2017, AI Mag..

[34]  David Maxwell Chickering,et al.  Machine Teaching: A New Paradigm for Building Machine Learning Systems , 2017, ArXiv.

[35]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[36]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[37]  Trevor Darrell,et al.  Grounding Visual Explanations , 2018, ECCV.

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

[39]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[40]  Subbarao Kambhampati,et al.  Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations , 2020, AAAI.