Trustworthy Artificial Intelligence. 3 credits, 3 contact hours

Catalog description

Prerequisites: DS 675 or approval of instructor. As machine learning (ML) systems are increasingly being deployed in real-world applications, it is critical to ensure that these systems are behaving responsibly and are trustworthy. That will lead to wider adoption of ML in real-world applications in practice. This course will provide a deep understanding of state-of-the-art ML methods designed to make AI more trustworthy to unforeseen faults, adversarial manipulation, and to violations of ethical norms in privacy and fairness. Students will gain an understanding of and experience in using a set of methods and tools for deploying transparent, ethically sound, and robust machine learning solutions. The course is also an excellent opportunity to conduct research on the security/privacy/trustworthiness in ML and find research topics for Ph.D. and M.S. theses.