
Prof. Derong Liu
Anhui University, China
Speech Title: Artificial Intelligence-Based Self-Learning Control Methods
Abstract: Artificial Intelligence-Based Self-Learning Control Methods have emerged as a transformative approach for optimal control of nonlinear systems in dynamic and complex environments. Unlike traditional control techniques that rely on predefined models and manual tuning, self-learning control leverages AI-driven algorithms, such as reinforcement learning and neural networks to adapt and optimize control strategies in real time. These methods enable autonomous decision-making, improved robustness, and enhanced adaptability, making them particularly useful in robotics, autonomous vehicles, industrial automation, and smart energy systems. This lecture explores the fundamental principles of AI-driven self-learning control, discusses key methodologies including adaptive dynamic programming and parallel control approaches, and examines their practical applications across various domains. Furthermore, this lecture also explores the trade-offs between learning efficiency, real-time adaptability, and deployment feasibility, offering insights into overcoming these challenges for real-world implementations. Additionally, the concept of meta-control is considered as a higher-level mechanism to dynamically adjust self-learning strategies, improving the efficiency and robustness of AI-driven control systems. By integrating AI with control theory, self-learning control is poised to revolutionize intelligent automation, enabling more efficient and autonomous systems.
Bio: Derong Liu earned his Ph.D. in electrical engineering from the University of Notre Dame in 1994. He served as a Staff Fellow at General Motors Research and Development Center from 1993 to 1995, and subsequently as an Assistant Professor in the Department of Electrical and Computer Engineering at Stevens Institute of Technology from 1995 to 1999. In 1999, Dr. Liu joined the University of Illinois Chicago, where he advanced to the position of Full Professor of Electrical and Computer Engineering and of Computer Science in 2006. He was selected for the prestigious “100 Talents Program” by the Chinese Academy of Sciences in 2008. He also served as the Associate Director of The State Key Laboratory of Management and Control for Complex Systems at the Institute of Automation from 2010 to 2016. Currently, Dr. Liu is Professor and Dean with the School of Artificial Intelligence at Anhui University, Hefei, China. He has authored 13 books and serves as the Editor-in-Chief of Artificial Intelligence Review (Springer). Previously, he served as the Editor-in-Chief of the IEEE Transactions on Neural Networks and Learning Systems from 2010 to 2015. Throughout his career, Dr. Liu has received several awards for his contributions to the field, including the Faculty Early Career Development Award from the National Science Foundation in 1999, the University Scholar Award from the University of Illinois from 2006 to 2009, and the Overseas Outstanding Young Scholar Award from the National Natural Science Foundation of China in 2008. He has also been honored with prestigious awards such as the Outstanding Achievement Award from Asia Pacific Neural Network Assembly in 2014, the INNS Gabor Award in 2018, the IEEE SMC Society Andrew P. Sage Best Transactions Paper Award in 2018, the IEEE TNNLS Outstanding Paper Award in 2018, the IEEE/CCA J. Automatica Sinica Hsue-Shen Tsien Paper Award in 2018, and the IEEE CIS Neural Network Pioneer Award in 2022. Consistently recognized as a highly cited researcher by Clarivate since 2017, Dr. Liu is a Fellow of the IEEE, the International Neural Network Society, and the International Association of Pattern Recognition. He is also a Member of Academia Europaea (The Academy of Europe).
中文简介:刘德荣,安徽大学人工智能学院教授,欧洲科学院院士,IEEE Fellow,INNS Fellow,IAPR Fellow,中国自动化学会会士、中国自动化学会常务理事,国家高层次人才计划入选者。1994年从美国圣母大学毕业获电气工程博士学位。从1999年开始,在芝加哥伊利诺伊大学电气与计算机工程系先后任助理教授(1999–2002)、终身职副教授(2002–2006)和终身职正教授(2006年起)。2008年,入选中国科学院“****”。曾任中国科学院自动化研究所复杂系统管理与控制国家重点实验室副主任(2010–2016)。长期致力于数据科学与人工智能、智能控制理论及应用领域的理论和关键技术创新,主持承担了科技部国家重点研发计划新一代人工智能课题和国家基金委重点项目。共发表了320多篇SCI论文、310多篇国际会议论文,同他人合作共出版过13本书,Google Scholar 总引用 3 万余次,H-index 100。获中国自动化学会自然科学奖一等奖两次,国际神经网络学会终身贡献奖,IEEE计算智能学会神经网络先驱奖,连续多年获得Clarivate高被引学者称号,曾分别获国家基金委杰青B类和美国国家基金会教授早期事业发展奖。曾任《IEEE神经网络与学习系统汇刊》主编、IFAC理事、亚太神经网络学会主席。现任IEEE广州分会主席、《人工智能评论》主编、World Scientific出版社Deep Learning Neural Networks系列丛书主编。

Prof. Zhongsheng Hou
Qingdao University, China
Speech Title: Brief History and Progress of MFAC Theory
Abstract: This talk includes three
parts. First parts will focus on the history background of
model free adaptive control (MFAC). The second is going to
talk the MFAC progress both in theory and applications, and
the relationships between MFAC with traditional adaptive
control, classical PID as well. The last is Conclusion.
Bio: Zhongsheng Hou received his Ph.D. degree from Northeastern University in 1994, Shenyang, China. From 1997 to 2018, he was with Beijing Jiaotong University, Beijing, China, where he was a Distinguished Professor and the Founding Director of Advanced Control Systems Lab, and the Head of the Department of Automatic Control. From 2002 to 2003, he was a visiting Professor at Yale University, USA. Currently he is a Chair Professor with Qingdao University, Qingdao, China.
Prof. Hou is the Founding Director of the Technical Committee ‘Data Driven Control, Learning and Optimization (DDCLO)’of the Chinese Association of Automation (CAA), and the Technical Committee ‘Data Driven Control Systems’ of the Asian Control Association. He is IEEE Fellow, CAA Fellow, and AAIA Fellow. Dr. Hou was the Leading Guest Editor for two Special Sections on the topic of data-driven control in IEEE Transactions on Neural Networks in 2011, and IEEE Transactions on Industrial Electronics in 2017.
His research interests are in the fields of data-driven control, model-free adaptive control, data driven learning control, and intelligent transportation systems. He has authored or co-author more than 300 journal papers, including 150+ IEEE Transactions papers, and two monographs, Nonparametric Model and its Adaptive Control Theory, Science Press, 1999 (in Chinese), and Model Free Adaptive Control: Theory and Applications, CRC Press, 2013. His publications have been cited 26000+ times in Google Scholar with H-index 78.
His pioneering works on Model-Free Adaptive Control (MFAC) theory and on Model Free Adaptive Iterative Learning Control (MFAILC) theory have been verified by more than 30 years of academic researches and practical applications in over 300 different fields, including wide-area power systems, lateral control of autonomous vehicles, temperature control of silicon rod, etc. Please see the details in website https://assc.qdu.edu.cn/ .
中文简介:侯忠生,1962生。1994年于东北大学获得博士学位,1997年哈尔滨工业大学博士后,2002-2003年美国耶鲁大学访问学者。原为北京交通大学自动控制系主任、二级教授、北京交通大学卓越百人计划“领军人才”入选者。现为青岛大学首席教授,系统科学研究院院长。
IEEE Fellow;中国自动化学会会士(CAA Fellow);IFAC Technical Committee "Adaptive and Learning Systems" 委员;IFAC Technical Committee "Transportation Systems"委员。
中国自动化学会“数据驱动控制、学习与优化”专业委员会创始主任;创办IEEE Data Driven Control and Learning Systems Conference会议,并任大会总主席。曾任或现任“自动化学报”、“控制理论与应用”、“控制与决策”、“系统科学与数学”编委;曾是IEEE神经元网络与学习系统会刊“基于数据的控制、决策、调度与故障诊断”专刊客座编委;IEEE工业电子学会刊专刊“数据驱动控制与学习系统”责任客座编委。

Prof. Zhen Lei
Institute of Automation Chinese Academy of Sciences, China
Speech Title: Continual and Generalizable AIGC Detection
Abstract: In this talk, I will introduce several recent works from our group for AIGC (especially face forgery) detection. The generalized detection model and the continue learning for detecting endless face forgery types are presented. The improvements are from the network structure design, data preparation/replay and loss function optimization. Specifically, the wavelet based Mamba for feature extraction, the forgery-discomfort learning and the joint face forgery detection and fine-grained artifact localization are presented for generalized foundation model learning. Developmental shared and orthogonal LoRA subspaces learning, KAN based function and direct discrepancy replay techniques are proposed to improve the continue learning performance of model update. Experimental results on various databases demonstrate the superiority of proposed methods.
Bio: Zhen Lei is a professor in Institute of Automation, Chinese Academy of Sciences, a distinguished guest professor in Macau University of Science and Technology. He is IEEE Fellow, IAPR Fellow and AAIA Fellow. He has published over 300 papers in international journals and conferences with 43000+ citations in Google Scholar and h-index 93. He is associate editor-in-chief of Pattern Recognition, senior area editor of IEEE Trans. on Information Forensics and Security and associate editor of IEEE Transactions on Biometrics, Behavior, and Identity Science. His research interests are in computer vision, pattern recognition, and image processing. He is the winner of 2019 IAPR Young Biometrics Investigator Award.
© 2020-2026 IEEE 7th International Conference on Computers and Artificial Intelligence Technologies--cait_conference@163.com.