This paper extends the work submitted by Gradient to the 2nd Ethics of Data Science Conference on fair regression in a number of ways. Firstly, the methods introduced in the earlier paper for quantifying the fairness of continuous decisions are benchmarked against “gold standard” (but typically intractable) techniques in order to test their efficacy.
Read more

A paper authored by Gradient Institute researchers has been accepted at the 2nd Ethics of Data Science Conference, to be held in Sydney from 25-27 March 2020. The paper studies the problem of how to create quantitative, mathematical representations of fairness that can be incorporated into AI systems to promote fair AI-driven decisions.
Read more

In this paper (to be presented at the second Ethics of Data Science Conference) we study the problem of how to create quantitative, mathematical representations of fairness that can be incorporated into AI systems to promote fair AI-driven decisions. For discrete decisions (such as accepting or rejecting a loan application), there are well established ways to quantify fairness.
Read more

Gradient Institute, along with the Centre of Translational Data Science from the University of Sydney and the Humanising Machine Intelligence project from the ANU is organising the second edition of the Ethics of Data Science Conference, which will take place from 25-27 March 2020 at the University of Sydney.
Read more

In this post we explain a Bayesian approach to inferring the impact of interventions or actions. We show that representing causality within a standard Bayesian approach softens the boundary between tractable and impossible queries and opens up potential new approaches to causal inference.
Read more