Recent advances in machine learning have led to novel AI-based solutions to challenging computational problems of societal importance. Yet, the state-of-the-art models do not provide reliable explanations of how they make decisions, and can make occasional mistakes on even simple problems. The resulting lack of assurance and trust are obstacles to their adoption in high stakes applications such as clinical decision making. In this talk, I will first explain the problem of forecasting impending cardiac arrest by monitoring ECG signals for in-hospital patients. Then I will discuss both exciting recent advances and remaining challenges in developing an AI-based solution that clinicians can trust and deploy.

Bio: Rajeev Alur is Zisman Family Professor of Computer and Information Science and the Founding Director of ASSET Center for Trustworthy AI at University of Pennsylvania. He obtained his bachelor's degree from IIT Kanpur and PhD from Stanford University. His research is focused on principles and tools for design and analysis of safe and trustworthy systems. He is a Fellow of AAAS, ACM, and IEEE, an Alfred P. Sloan Faculty Fellow, and a Simons Investigator. Notable awards include the CAV (Computer-Aided Verification) award, the Alonzo Church award in logic and computation, IIT Kanpur Distinguished Alumnus Award, and the Knuth Prize in theoretical computer science. He is the author of the textbook Principles of Cyber-Physical Systems (MIT Press), was the lead PI of the NSF Expeditions in Computing project ExCAPE on program synthesis, and is the General Chair of Federated Logic Conference (FLoC).