报告学者：YangQuan Chen

报告者单位：University of California Merced

报告时间：2025/07/05  08:40-09:15

报告地点：红果园三层多功能厅

Abstract:  It is time not only to ask what AI/ML can do for control but also ask what control (theories) can do for AI/ML. It is like a coin’s two sides: ML4Control and Control4ML. This talk will focus on how control theory will enable us to rigorously analyze and synthesize AI/ML algorithms such that by bridging control theory and M such that AI/ML algorithms are both high-performing and provably stable, robust, and efficient. We begin with control theory point of view of ML process by treating ML process as a dynamic system that is a possibly controlled dynamic process. Then we discuss ML algorithm analysis via control theory, as well as ML algorithm design via control theory. Control theory can be generally classified as integer order control theory (IOCT) and fractional order control theory (FOCT). This talk will be of tutorial nature covering both integer order and fractional order control for machine learning algorithms analysis and design.

报告学者简介：YangQuan Chen earned his Ph.D. from Nanyang Technological University, Singapore, in 1998. He had been a faculty of Electrical Engineering at Utah State University (USU) from 2000-12. He joined the School of Engineering, University of California, Merced (UCM) in summer 2012 teaching “Mechatronics”, “Digital Twins”, “Engineering Service Learning” and “Unmanned Aerial Systems” for undergraduates; “Fractional Order Mechanics”, “Linear Multivariable Control”, “Nonlinear Controls” and “Advanced Controls: Optimality and Robustness” for graduates. His research interests include mechatronics for sustainability, cognitive process control (smart control engineering enabled by digital twins), small multi-UAV based cooperative multi-spectral “personal remote sensing”, applied fractional calculus in controls, modeling and complex signal processing; distributed measurement and control of distributed parameter systems with mobile actuator and sensor networks. He received Research of the Year awards from USU (2012) and UCM (2020). He was listed in Highly Cited Researchers by Clarivate Analytics in 2018-2021. Most recently he started with Dr. Bruce J. West a new book series of CRC Press on AFC4STEM (Fractional Order Thinking in Exploring the Frontiers of STEM) and established a new section for Fractals and Fractional journal on “Optimization, big data and AI/ML”. His Google Scholar citations are over 59780 with H-index 106, H-10 index 683.