10-712 Fairness, Explainability, and Accountability for Machine Learning

6 units, Carnegie Mellon University

As ML continues to advance and make its way into various aspects of our lives, both the designers and users of the technology need to think seriously about its impact on individuals and society. We will study some of the ethical implications of applying ML tools to highstakes consequential domains, such as employment, education, credit lending, and criminal justice. We will discuss at length how an ML model can end up making unfair or discriminatory predictions who should be held responsible when MLassisted decisions negatively impact certain demographic groups or individuals and last but not least, how such decisions can be explained to a nontechnical audience. Throughout the course, we will mainly focus on technical remedies that have been recently proposed by the ML community to tackle the above issues, and critically discuss their advantages and shortcomings.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.