Introduction to AI Fairness

Abstract

Today, AI is used in many high-stakes decision-making applications in which fairness is an important concern. Already, there are many examples of AI being biased and making questionable and unfair decisions. Recently, the AI research community has proposed many methods to measure and mitigate unwanted biases, and developed open-source toolkits for developers to make fair AI. This course will cover the recent development in algorithmic fairness, including the many different definitions of fairness, their corresponding quantitative measurements, and ways to mitigate biases. This course is open to beginners and is designed for anyone interested in the topic of AI fairness.