Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learning
Philosophy and Technology 33 (3):487-502 (2020)
AbstractThe 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.
Added to PP
Historical graph of downloads
References found in this work
Scientific Explanation and the Causal Structure of the World.Wesley C. Salmon - 1984 - Princeton University Press.
The Ethics of Algorithms: Mapping the Debate.Brent Mittelstadt, Patrick Allo, Mariarosaria Taddeo, Sandra Wachter & Luciano Floridi - 2016 - Big Data and Society 3 (2).
Studies in the Logic of Explanation.Carl Gustav Hempel & Paul Oppenheim - 1948 - Philosophy of Science 15 (2):135-175.
Citations of this work
What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
Algorithmic Bias: Senses, Sources, Solutions.Sina Fazelpour & David Danks - 2021 - Philosophy Compass 16 (8):e12760.
Ethics as a Service: A Pragmatic Operationalisation of AI Ethics.Jessica Morley, Anat Elhalal, Francesca Garcia, Libby Kinsey, Jakob Mökander & Luciano Floridi - manuscript
Ethics as a service: a pragmatic operationalisation of AI ethics.Jessica Morley, Anat Elhalal, Francesca Garcia, Libby Kinsey, Jakob Mökander & Luciano Floridi - 2021 - Minds and Machines 31 (2):239–256.
Understanding Deep Learning with Statistical Relevance.Tim Räz - 2022 - Philosophy of Science 89 (1):20-41.
Similar books and articles
The Pragmatic Turn in Explainable Artificial Intelligence (XAI).Andrés Páez - 2019 - Minds and Machines 29 (3):441-459.
The Closed Fragment of the Interpretability Logic of PRA with a Constant For.Joost J. Joosten - 2005 - Notre Dame Journal of Formal Logic 46 (2):127-146.
Interpretability Over Peano Arithmetic.Claes Strannegard - 1999 - Journal of Symbolic Logic 64 (4):1407-1425.
Interpretability Over Peano Arithmetic.Claes Strannegård - 1999 - Journal of Symbolic Logic 64 (4):1407-1425.
Interpretability Degrees of Finitely Axiomatized Sequential Theories.Albert Visser - 2014 - Archive for Mathematical Logic 53 (1-2):23-42.
A Cut-Free Sequent System for the Smallest Interpretability Logic.Katsumi Sasaki - 2002 - Studia Logica 70 (3):353-372.
Interpolation and the Interpretability Logic of PA.Evan Goris - 2006 - Notre Dame Journal of Formal Logic 47 (2):179-195.
Interpretability In.Marta Bílková, Dick de Jongh & Joost J. Joosten - 2010 - Annals of Pure and Applied Logic 161 (2):128-138.
Symbol Grounding is an Empirical Problem: Neural Nets Are Just a Candidate Component.Stevan Harnad - 1993
On Interpretability of Almost Linear Orderings.Akito Tsuboi & Kentaro Wakai - 1998 - Notre Dame Journal of Formal Logic 39 (3):325-331.
Provability Logics for Relative Interpretability.Frank Veltman & Dick De Jongh - 1990 - In Petio Petrov Petkov (ed.), Mathematical Logic. Proceedings of the Heyting '88 Summer School. New York, NY, USA: pp. 31-42.