The Penn State Berks Artificial Intelligence, Modeling and Simulation Laboratory (AIMS Lab) will host a presentation on how artificial intelligence (AI) can be made fairer in consequential decisions. The lecture will be presented by Violet (Xinying) Chen, an assistant professor of information systems and analytics at Stevens Institute of Technology, from noon to 1 p.m., Tuesday, Nov. 17, in the Gaige Technology and Business Innovation Building, Room 244. The seminar is free and open to the public. Advanced registration is required.
The lecture, titled "Foundations of ethics and algorithmic fairness towards responsible AI," will examine how AI systems, such as those used in healthcare, lending and content moderation, may disadvantage the people they are intended to serve. Chen will explain different ways to define fairness, including parity-based and utility-based approaches, and why some fairness goals cannot always be satisfied at the same time. She also will discuss when those goals can be reconciled and how interventions, either before model training or after deployment, can improve fairness.
The talk will conclude with discussion about fairness in generative AI, where equitable output can be difficult to define. Chen will also discuss oversight of autonomous agents that may operate without a person reviewing each decision.
Chen earned a doctorate in operations research from Carnegie Mellon University. She studies fairness and ethics in decision-making using optimization and AI. She has received a U.S. National Science Foundation grant for her research and her studies have been published in the European Journal of Operational Research, Annals of Operations Research, Association for the Advancement of Artificial Intelligence and Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research.
The mission of the Penn State Berks AIMS Lab is to educate the community about intelligent technologies, help local organizations make research-informed decisions and prepare future data analytics and AI professionals. AIMS Lab's guest seminars are open to Penn State faculty, staff and students and the public.
