Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence

Philosophy and Technology 34 (2):265-288 (2021)
  Copy   BIBTEX

Abstract

Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. Explainable Artificial Intelligence aims to develop analytic techniques that render opaque computing systems transparent, but lacks a normative framework with which to evaluate these techniques’ explanatory successes. The aim of the present discussion is to develop such a framework, paying particular attention to different stakeholders’ distinct explanatory requirements. Building on an analysis of “opacity” from philosophy of science, this framework is modeled after accounts of explanation in cognitive science. The framework distinguishes between the explanation-seeking questions that are likely to be asked by different stakeholders, and specifies the general ways in which these questions should be answered so as to allow these stakeholders to perform their roles in the Machine Learning ecosystem. By applying the normative framework to recently developed techniques such as input heatmapping, feature-detector visualization, and diagnostic classification, it is possible to determine whether and to what extent techniques from Explainable Artificial Intelligence can be used to render opaque computing systems transparent and, thus, whether they can be used to solve the Black Box Problem.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 76,442

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

Socially useful artificial intelligence.Richard Ennals - 1987 - AI and Society 1 (1):5-15.
Abductive Reasoning.Douglas Walton - 2004 - Tuscaloosa, AL, USA: University Alabama Press.
A competence framework for artificial intelligence research.Lisa Miracchi - 2019 - Philosophical Psychology 32 (5):588-633.
Ethical Machines?Ariela Tubert - 2018 - Seattle University Law Review 41 (4).

Analytics

Added to PP
2019-12-21

Downloads
99 (#126,970)

6 months
19 (#57,658)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Carlos Zednik
Eindhoven University of Technology