EXPLAINING EXPLANATION FOR “EXPLAINABLE AI”

摘要

What makes for an explanation of "black box" AI systems such as Deep Nets? We reviewed thepertinent literatures on explanation and derived key ideas. This set the stage for our empiricalinquiries, which include conceptual cognitive modeling, the analysis of a corpus of cases of"naturalistic explanation" of computational systems, computational cognitive modeling, and thedevelopment of measures for performance evaluation. The purpose of our work is to contribute tothe program of research on “Explainable AI.” In this report we focus on our initial syntheticmodeling activities and the development of measures for the evaluation of explainability inhuman-machine work systems.