Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Explaining explanations in AI
Mittelstadt B., Russell C., Wachter S.  FAT* 2019 (Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, Jan 29-31, 2019)279-288.2019.Type:Proceedings
Date Reviewed: Feb 21 2020

Everyone agrees that artificial intelligence (AI) should be explainable; there is even an abbreviation for this: xAI. But opinions differ on what it means. This paper is a survey of different approaches to xAI.

Ideally, AI systems should provide fully transparent recommendations, that is, recommendations that come from a sequence of clear, agreed-upon rules. In practice, this is rarely possible. Even when we can formulate such rules, the derivation is usually too long for a human to grasp. A usual alternative is to use, as an explanation, a derivation in a simplified easier-to-grasp model--just like simple approximate physical reasoning helps us understand the results of solving complex physical equations.

However, in physics, we usually understand how accurate an approximate model is and what the limits of its applicability are, while most xAI systems do not provide this information and thus tend to apply the simplified models even when they are not applicable. Also, the systems explain why a certain conclusion A was made; however, the user is also interested in contrastive explanations: why A and not B?

In general, users would like the systems to be interactive. They should be able to ask, for example, what can we do to change the recommendation to B? What is the evidence behind the rules? They should be able to argue when the recommendations and/or rules seem unfair. In view of these user needs, the paper surveys current attempts to design contrastive and interactive xAI.

Reviewer:  V. Kreinovich Review #: CR146901 (2008-0194)
Bookmark and Share
  Featured Reviewer  
 
General (I.0 )
 
 
Cognitive Simulation (I.2.0 ... )
 
Would you recommend this review?
yes
no
Other reviews under "General": Date
A multi-modal approach for determining speaker location and focus
Siracusa M., Morency L., Wilson K., Fisher J., Darrell T.  Multimodal interfaces (Proceedings of the 5th international conference, Vancouver, British Columbia, Canada, Nov 5-7, 2003)77-80, 2003. Type: Proceedings
Mar 1 2004
Nanotechnology: science and computation (Natural Computing Series)
Chen J., Jonoska N., Rozenberg G., Springer-Verlag New York, Inc., Secaucus, NJ, 2006.  393, Type: Book (9783540302957)
Aug 2 2007
High performance computing for big data: methodologies and applications
Wang C., CRC Press, Inc., Boca Raton, FL, 2018.  286, Type: Book (978-1-498783-99-6), Reviews: (1 of 2)
Apr 4 2019
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy