Back to Search
Start Over
Transparency as design publicity: explaining and justifying inscrutable algorithms
- Source :
- Ethics and Information Technology, 23 (3), Ethics and Information Technology
- Publication Year :
- 2020
- Publisher :
- Springer Science and Business Media LLC, 2020.
-
Abstract
- In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.
- Subjects :
- Cognitive science
Counterfactual thinking
Concepts and models
Computer science
media_common.quotation_subject
610 Medicine & health
Justifications
02 engineering and technology
Procedural justice
Library and Information Sciences
Transparency
0603 philosophy, ethics and religion
Machine learning
Explanations
Philosophy of science
Computing methodologies ~ Artificial intelligence
Human-centered computing ~ HCI theory
Argument
Black box
020204 information systems
1706 Computer Science Applications
0202 electrical engineering, electronic engineering, information engineering
Product (category theory)
Interpretability
media_common
Abstraction (linguistics)
Original Paper
06 humanities and the arts
16. Peace & justice
Transparency (behavior)
Computer Science Applications
10222 Institute of Biomedical Ethics and History of Medicine
Normative
020201 artificial intelligence & image processing
3309 Library and Information Sciences
060301 applied ethics
Publicity
Algorithm
Subjects
Details
- ISSN :
- 15728439 and 13881957
- Volume :
- 23
- Database :
- OpenAIRE
- Journal :
- Ethics and Information Technology
- Accession number :
- edsair.doi.dedup.....f0630c135163d7c121973a7ce999e550