Explaining Explanations in AI.

Explainable AI
Critique
Paper
Author

Published

January 1, 2019

Description

Mittelstadt, Russell, and Wachter (2019) points out that there is a gap in the understanding of what explanations are between computer scientists and explanation scientists (social scientists, cognitive scientists, pyschologists, …). Current methods produce at best locally reliable explanations. There needs to be shift towards interactive explanations.

References

Mittelstadt, Brent, Chris Russell, and Sandra Wachter. 2019. “Explaining Explanations in AI.” In Proceedings of the Conference on Fairness, Accountability, and Transparency, 279–88.