This course provides a structured introduction to fairness in AI and data-driven decision-making, using probability, statistics, and supervised machine learning as foundations. Participants will learn how bias can emerge in datasets and models. The course combines conceptual understanding with practical demonstrations of a fairness analysis tool, enabling both technical and non-technical learners to confidently interpret fairness results and make responsible, data-informed decisions.
By the end of this course, learners will be able to identify fairness risks, interpret statistical and fairness metrics, and use a fairness tool to assess whether AI systems treat different groups equitably.
- Teacher: Prathyusha Sagi