CS 498 MLG - Trustworthy ML
Last offered Fall 2022
Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: 1 to 4 undergraduate hours. 1 to 4 graduate hours. May be repeated in the same or separate terms if topics vary.
As machine learning (ML) systems and platforms are increasingly being deployed in real-world applications, especially those in high-stakes domains, e.g., credit scoring, criminal justice, predictive policing, hiring decisions, etc., it is critical to ensure that these systems are behaving responsibly and are trustworthy. To this end, there has been growing interest from researchers and practitioners to develop and deploy ML models and algorithms that are not only accurate, but also fair, interpretable, robust and privacy-preserving. This broad area of research is commonly referred to as trustworthy ML. This course will cover topics within the broad area of trustworthy ML, including algorithmic fair- ness, model interpretability, model robustness to distributional shift, adversarial robustness, and differential privacy. Prerequisites include probability and statistics, linear algebra and calculus. The course will be self-contained, and existing knowledge about machine learning algorit
|Trustworthy ML||MLG||68912||LEC||4||1400 - 1515||T R||4025 Campus Instructional Facility||Han Zhao|