The Concepts of Risk and Safety

By Niklas Möller. 2012

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products (2016, background): “In particular, a general definition of safety is the minimization of risk andepistemic uncertainty(understood in the usual decision-theoretic senses of the words) associated w i h unwanted outcomes that are severe enough to be seen as harmful [3].”
Increasing Trust in AI Services through Supplier's Declarations of Conformity (2018, background): “Safety, discussed in [5, 2] as the minimization of both risk and epistemic uncertainty, will include explainability, algorithmic fairness, and robustness to concept drift.”
FactSheets: Increasing trust in AI services through supplier's declarations of conformity (2019, background): “Safety, discussed in [3] and [5] as the minimization of both risk and epistemic uncertainty, will include explainability, algorithmic fairness, and robustness to dataset shift.”
A survey of deep learning techniques for autonomous driving (2019, background): “Enlarging the scope of safety, Möller (2012) proposes a decision‐ theoretic definition of safety that applies to a broad set of domains and systems.”
FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity. (2018, background): “Safety, discussed in [5, 3] as the minimiza-”
Engineering safety in machine learning (2016, background): “Predictions made by machine learning systems in applications such as medical diagnosis [8], loan approval [9], and prison sentencing [10] can have a profound effect on people; undesired outcomes are truly harmful in a human sense.”