Explaining Explanation, Part 4: A Deep Dive on Deep Nets
Document Type
Article
Publication Date
5-1-2018
Abstract
© 2001-2011 IEEE. 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.
Publication Title
IEEE Intelligent Systems
Recommended Citation
Hoffman, R.,
Miller, T.,
Mueller, S.,
Klein, G.,
&
Clancey, W.
(2018).
Explaining Explanation, Part 4: A Deep Dive on Deep Nets.
IEEE Intelligent Systems,
33(3), 87-95.
http://doi.org/10.1109/MIS.2018.033001421
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/10787