Trustworthy AI

Catalog description

As Artificial Intelligence (AI) 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 a wider adoption of AI in real-world applications in practice. This course will provide a deep understanding of state-of-the-art AI 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 security/privacy/trustworthiness in AI. This course will cover the fundamentals of ML and techniques to make ML become trustworthy as well as the technical background to implement basic TML techniques in a deep learning framework using Python. Prerequisite(s): C YBR 108 or C INF 108 or I CSI/I ECE 201.