Explaining Explanation, Part 4: A Deep Dive on Deep Nets

This is the fourth in a series of essays about explainable AI. Previous essays laid out the theoretical and empirical foundations. This essay focuses on Deep Nets, and con-siders methods for allowing system users to generate self-explanations. This is accomplished by exploring how the Deep Net systems perform when they are operating at their boundary conditions. Inspired by recent research into adversarial examples that demonstrate the weakness-es of Deep Nets, we invert the purpose of these adversar-ial examples and argue that spoofing can be used as a tool to answer contrastive explanation questions via user-driven exploration.

[1]  Keith A. Markus,et al.  Making Things Happen: A Theory of Causal Explanation , 2007 .

[2]  Gary Klein,et al.  Explaining Explanation, Part 2: Empirical Foundations , 2017, IEEE Intelligent Systems.

[3]  Thomas R. Gruber,et al.  Learning why by being told what: interactive acquisition of justifications , 1991, IEEE Expert.

[4]  William R. Swartout,et al.  A Digitalis Therapy Advisor with Explanations , 1977, IJCAI.

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

[6]  Ananthram Swami,et al.  Practical Black-Box Attacks against Machine Learning , 2016, AsiaCCS.

[7]  James A. Overton.  “Explain” in scientific discourse , 2013, Synthese.

[8]  Gary Klein,et al.  Explaining Explanation, Part 1: Theoretical Foundations , 2017, IEEE Intelligent Systems.

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

[10]  Gary Klein,et al.  Explaining Explanation, Part 3: The Causal Landscape , 2018, IEEE Intelligent Systems.

[11]  J. L. Weiner,et al.  BLAH, A System Which Explains its Reasoning , 1980, Artif. Intell..

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

[13]  William B. Thompson,et al.  Reconstructive Expert System Explanation , 1992, Artif. Intell..

[14]  J. Mill.  A System Of Logic, Ratiocinative And Inductive , 2019 .

[15]  James R. Slagle,et al.  The partitioned support network for expert system justification , 1989, IEEE Trans. Syst. Man Cybern..

[16]  Edward H. Shortliffe,et al.  Rule Based Expert Systems: The Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in artificial intelligence) , 1984 .

[17]  Jason Yosinski,et al.  Deep neural networks are easily fooled: High confidence predictions for unrecognizable images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Alun D. Preece,et al.  Interpretability of deep learning models: A survey of results , 2017, 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[19]  Marek J. Druzdzel,et al.  Explanation in Probabilistic Systems: Is It Feasible? Will It Work? , 2001 .

[20]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[21]  William J. Clancey,et al.  Knowledge-based tutoring: the GUIDON program , 1987 .

[22]  Ruth M. J. Byrne,et al.  Counterfactual Thinking: From Logic to Morality , 2017 .