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

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 modelled 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.

Tags
Data and Resources
To access the resources you must log in
  • BibTeXBibTeX

    The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
  • htmlHTML

    The resource: 'html' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Author Zednik, Carlos, carlos.zednik@ovgu.de, orcid.org/0000-0002-9702-7706
DOI https://doi.org/10.1007/s13347-019-00382-7
Group Explainable Machine Learning
Group Ethics and Legality
Publisher Springer
Source Philosophy & Technology (2019)
Thematic Cluster Other
system:type JournalArticle
Management Info
Field Value
Author Pozzi Giorgia
Maintainer Pozzi Giorgia
Version 1
Last Updated 5 March 2021, 13:00 (CET)
Created 9 February 2021, 23:35 (CET)