3.0

credits

Average Course Rating

Machine learning systems have huge capabilities, and they are increasingly being deployed in many real-world applications. Therefore, it is critical to make sure that they are safe and trustworthy. This course focuses on understanding aspects regarding fairness, privacy, explainability, and robustness of machine learning models. The course will cover a list of recent research papers in the field, featuring practical aspects as well as mathematical aspects of these topics. The course not only focuses on the theory of fairness, privacy, explainablity, and robustness of machine learning models, but also it aims to develop students' communication skills.