University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Explaining Explanations in AI

Mittelstadt, Brent, Russell, Christopher and Wachter, Sandra (2019) Explaining Explanations in AI In: FAT* '19 Proceedings of the Conference on Fairness, Accountability, and Transparency.

[img]
Preview
Text
Explaining Explanations in AI.pdf - Accepted version Manuscript
Available under License Creative Commons Attribution.

Download (846kB) | Preview

Abstract

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Mittelstadt, Brent
Russell, Christopherchris.russell@surrey.ac.uk
Wachter, Sandra
Date : 29 January 2019
DOI : 10.1145/3287560.3287574
Copyright Disclaimer : © 2019 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-6125-5/19/01
Depositing User : Rebecca Cooper
Date Deposited : 15 Mar 2019 11:25
Last Modified : 15 Mar 2019 11:25
URI: http://epubs.surrey.ac.uk/id/eprint/850740

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800