notice
CIISE - INVITED SPEAKER SEMINAR - Bridging Learning and Control in Networked Cyber-Physical Environments
Dr. Xiangnan Zhong, Associate Professor, Department of
Date: Wednesday, November 12, 2025, at 10:00 a.m.
Location: EV 1.162
Abstract
With the rapid advancement of brain science and modern technologies, developing efficient approaches for brain-like intelligent systems has become an important frontier in control and learning research. Among various efforts toward this goal, reinforcement learning (RL) has emerged as a core methodology for achieving brain-inspired intelligence in control, decision-making, and optimization. The progress in RL offers new opportunities to realize such intelligence within complex cyber-physical systems (CPS) across multiple domains. In this talk, I will present data-driven intelligent control methods for networked cyber-physical systems characterized by distributed and interactive structures. These methods incorporate mechanisms that mimic human learning by exploring, adapting, and improving through continual interaction with dynamic environments. Unlike classical control approaches that rely on detailed system models, the proposed framework enables adaptive and resilient coordination among networked agents by interacting physical systems when the systems with which they interact may react in inconsistent ways.
Biography
Dr. Xiangnan Zhong is an Associate Professor in the Department of Electrical Engineering and Computer Science (EECS). Her research interests span computational intelligence, reinforcement learning, cyber-physical systems, networked control systems, neural networks, and optimal control. She has received several prestigious recognitions, including the National Science Foundation (NSF) Faculty Early Career Development (CAREER) Award in 2021 and the NSF CRII Award in 2019. Additionally, she was a recipient of the International Neural Network Society (INNS) Aharon Katzir Young Investigator Award in 2021. She currently serves as an Associate Editor for IEEE Transactions on Neural Networks and Learning Systems (since 2021) and IEEE Internet of Things Journal (since 2023).