5th seminar - Conformal Prediction for Reliable AI-Based Wireless Communications
Title: Conformal Prediction for Reliable AI-Based Wireless Communications
Time: 10:30am on 20th Feb. 2024 Location: 909B, EEE Building
Abstract: Artificial intelligence (AI) is widely viewed as a transformative technology in many engineering domains, including telecommunications. Before they are adopted at a large scale, however, AI tools need to be shown to offer the same verifiable reliability guarantees expected from conventional model-based methods. This talk provides a tutorial-style introduction to conformal prediction and conformal risk control, two statistical techniques that provide assumption-free formal guarantees of reliability. Examples of applications for wireless systems are presented, and open problems are highlighted.
Bio: Osvaldo Simeone is a Professor of Information Engineering. He co-directs the Centre for Intelligent Information Processing Systems within the Department of Engineering of King's College London, where he also runs the King's Communications, Learning and Information Processing lab. He is also a visiting Professor with the Connectivity Section within the Department of Electronic Systems at Aalborg University. He received an M.Sc. degree (with honors) and a Ph.D. degree in information engineering from Politecnico di Milano, Milan, Italy, in 2001 and 2005, respectively. From 2006 to 2017, he was a faculty member of the Electrical and Computer Engineering (ECE) Department at New Jersey Institute of Technology (NJIT), where he was affiliated with the Center for Wireless Information Processing (CWiP). His research interests include information theory, machine learning, wireless communications, neuromorphic computing, and quantum machine learning. He is the recipient of several best-paper awards, and he has led many projects supported by industry and funding organizations. Prof. Simeone is the author of the textbook "Machine Learning for Engineers" published by Cambridge University Press, four monographs, two edited books, and more than 200 research journal and magazine papers. He is a Fellow of the IET, EPSRC, and IEEE.