City Research Online

Abstract

We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and comprehensible systems that emit symbols enabling user-driven explanations of how a conclusion is reached. The paper is motivated by a corpus analysis of NIPS, ACL, COGSCI, and ICCV/ECCV paper titles showing differences in how work on explainable AI is positioned in various fields. We close by introducing a fourth notion: truly explainable systems, where automated reasoning is central to output crafted explanations without requiring human post processing as final step of the generative process.

Publication Type:	Article
Additional Information:	Copyright © 2018 for this paper by its authors. Copying permitted for private and academic purposes. Proceedings of the First International Workshop on Comprehensibility and Explanation in AI and ML 2017 co-located with 16th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2017) Bari, Italy, November 16th and 17th, 2017.
Publisher Keywords:	cs.AI
Departments:	School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads