Expert Review: Fairness Workshop

Description

There is an increasing awareness that AI systems can reproduce – and even amplify – unfairness in our society. From facial recognition systems that discriminate against people of colour to hiring algorithms favouring men over women, how can we understand and mitigate this problem?

In this hands-on workshop, you will learn to use a fairness evaluation metric. In the first part of the workshop, we will use Fairlearn, an open-source, community-driven library that gives insight and helps improve the fairness of machine learning algorithms. In the second part of the workshop, we will guide you to translate this newly acquired knowledge and skills to your work and dataset and more critically examine the broader issue around AI fairness.

We will work with Jupyter Notebook for this workshop, so it is necessary to bring a computer with Python and Jupyter Notebook already installed. In addition, we encourage you to bring your own cases (data) to the workshop.

Period	20 Oct 2023