Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning

Philosophy and Technology 33 (3):487-502 (2020)
  Copy   BIBTEX

Abstract

The usefulness of machine learning algorithms has led to their widespread adoption prior to the development of a conceptual framework for making sense of them. One common response to this situation is to say that machine learning suffers from a “black box problem.” That is, machine learning algorithms are “opaque” to human users, failing to be “interpretable” or “explicable” in terms that would render categorization procedures “understandable.” The purpose of this paper is to challenge the widespread agreement about the existence and importance of a black box problem. The first section argues that “interpretability” and cognates lack precise meanings when applied to algorithms. This makes the concepts difficult to use when trying to solve the problems that have motivated the call for interpretability. Furthermore, since there is no adequate account of the concepts themselves, it is not possible to assess whether particular technical features supply formal definitions of those concepts. The second section argues that there are ways of being a responsible user of these algorithms that do not require interpretability. In many cases in which a black box problem is cited, interpretability is a means to a further end such as justification or non-discrimination. Since addressing these problems need not involve something that looks like an “interpretation” of an algorithm, the focus on interpretability artificially constrains the solution space by characterizing one possible solution as the problem itself. Where possible, discussion should be reformulated in terms of the ends of interpretability.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 103,401

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Real Sparks of Artificial Intelligence and the Importance of Inner Interpretability.Alex Grzankowski - forthcoming - Inquiry: An Interdisciplinary Journal of Philosophy.
What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
Allure of Simplicity.Thomas Grote - 2023 - Philosophy of Medicine 4 (1).
The virtues of interpretable medical AI.Joshua Hatherley, Robert Sparrow & Mark Howard - 2024 - Cambridge Quarterly of Healthcare Ethics 33 (3):323-332.

Analytics

Added to PP
2019-08-13

Downloads
348 (#84,855)

6 months
21 (#132,862)

Historical graph of downloads
How can I increase my downloads?