Ethics and Information Technology · 2020 · 77 citations · 22 references
ComputingComputer ScienceDesignAlgorithmsArtificial IntelligenceMachine LearningEthics Of Automated Decision-makingExplainable Machine LearningExplanationTransparency MeasuresArtificial Intelligence TransparencyExplainabilityExplainable Artificial IntelligencePost Hoc ExplanationsTransparencyTransparency In Algorithms
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.
22
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations
Algorithmic Decision Making and the Cost of Fairness
Sam Corbett‐Davies, Emma Pierson, Avi Feller et al. · 2017 · 1.1K citations
Law, Criminal Law, Criminology +15
On the Morality of Artificial Agents
Luciano Floridi, J. W. Sanders · Minds and Machines · 2004 · 1.1K citations
Fairness in Criminal Justice Risk Assessments: The State of the Art
Richard A. Berk, Hoda Heidari, Shahin Jabbari et al. · Sociological Methods & Research · 2018 · 992 citations
Brent Mittelstadt, Chris Russell, Sandra Wachter · 2019 · 725 citations · Full text
Computing, Philosophy, Sociology +10