Keynote Speakers
FENG Gang
City University of Hong Kong
Gang FENG received the B.Eng and M.Eng. Degrees in Automatic Control from Nanjing Aeronautical Institute, China in 1982 and in 1984 respectively, and the Ph.D. degree in Electrical Engineering from the University of Melbourne, Australia in 1992. Professor Feng was a Lecturer in Royal Melbourne Institute of Technology, 1991 and a Senior Lecturer/Lecturer, University of New South Wales, 1992-1999. He has been with City University of Hong Kong since 2000, where he is now a Chair Professor of Mechatronic Engineering. He has received Alexander von Humboldt fellowship, the IEEE Computational Intelligence Society Fuzzy Systems Pioneer Award, the IEEE Transactions on Fuzzy Systems Outstanding Paper Award, the outstanding research award and President award of City University of Hong Kong, and several best conference paper awards. He is listed as a SCI highly cited researcher by Clarivate Analytics since 2016. His research interests include intelligent systems and control, networked control systems, and multi-agent systems and control. Professor Feng is a fellow of IEEE. He has been an Associate Editor of IEEE Trans. Automatic Control, IEEE Trans. on Fuzzy Systems, IEEE Trans. Systems, Man, & Cybernetics, Mechatronics, Journal of Systems Science and Complexity, Autonomous Intelligent Systems, Guidance, Navigation & Control, and Journal of Control Theory and Applications. He is also on the advisory board of Unmanned Systems.
Keynote Title
Intelligent Fuzzy Control
Keynote Abstract
This talk first gives a brief review on intelligent fuzzy control, including some fundamental concepts of fuzzy systems, conventional fuzzy control, and model based fuzzy control. It then discusses universal fuzzy controller problems for continuous-time multi-input-multi-output general nonlinear systems based on a class of generalized dynamic fuzzy dynamic models, often called Takagi-Sugeno fuzzy models. It is shown that this class of generalized dynamic fuzzy models can be used to approximate general nonlinear systems. By using their approximation capability, several results on universal fuzzy controllers for general nonlinear systems are then provided. Finally, some challenges in intelligent fuzzy control are also revealed.
Li Huimin
University of Science and Technology of China
Prof. Li Huimin graduated from the University of Science and Technology of China (USTC) with a Ph.D. in Condensed Matter Physics in June 2005. He is an executive member of the High-Performance Computing Professional Committee of the China Computer Federation. Currently, he serves as the Deputy Director of the Network Information Center of USTC, as well as the Deputy Director of the university's Supercomputing Center. He has long been engaged in research on supercomputing platform construction.
Keynote Title
The Application of Supercomputing Platform Construction and Its Supporting Role for Research-Oriented Universities
Keynote Abstract
Computational science is one of the three major sciences that drive human civilization and technological development, alongside experimental and theoretical sciences. Supercomputing plays an important supporting role in scientific research. The University of Science and Technology of China is a research-oriented university where numerous scientific research projects rely on supercomputing. This report introduces the main work of USTC that relies on supercomputing and the scientific research applications of its supercomputing center.
Yu Sun
Tsinghua University Press, Beijing, China
Yu Sun, Tsinghua University Press, Beijing, China Yu Sun, Ph.D., senior editor, is the Associate General Editor of Tsinghua University Press. She is also the adjunct researcher of Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences and the Vice President of Ecological Health Research Institute, Shandong University. She was selected as one of the Leading Talents in China's Press and Publishing Industry. Dr. Sun received doctorates in both medicine and management. She has more than 20 years experience in medical publishing. Her research focuses on medical academic evolution and established cited database in medical monograph for the first time. She has published in medical journals including The Lancet Public Health. She is the editorial office director of Cancer Innovation, iLIVER, Medicine Advances，iLABMED，iRADIOLOGY, Infectious Medicine，and Health Care Science.
Keynote Title
How to write seven statements in a standardized way
Keynote Abstract
Introduce and explain funding information, acknowledgment, conflict of interest statement, author contributions, data availability statement, ethics statement, and informed consent statement in detail.
Yuxi Li
RL4RealLife.org
Dr. Yuxi Li obtained his PhD in CS from the University of Alberta. On reinforcement learning for real life, he is the lead co-chair for NeurIPS 2022 and ICML 2021/2019 Workshops (https://sites.google.com/view/rl4reallife/), and the lead guest editor (twice) for the Machine Learning Journal Special Issue. He authored a 150-page deep RL overview, with 1200+ citations, https://bit.ly/2AidXm1, and Reinforcement Learning in Practice: Opportunities and Challenges, https://arxiv.org/abs/2202.11296. He reviews for AAAI, ACM CSUR, CACM, JAIR, JMLR, NeurIPS, TKDD, etc. Founder of RL4RealLife.org.
Keynote Title
Reinforcement learning for language models: iterative improvements from feedback
Keynote Abstract
Large language models like ChatGPT are phenomenal, however, with issues like hallucinations and lack of planning. We may leverage language models by prompting, fine-tuning, and augmenting with tools and APIs, potentially with smaller and/or specialized language models, to handle tasks. However, fully autonomous agents are not ready, since language models still make mistakes. Previous study shows that grounding, agency and interaction are the cornerstone for language models. We argue that iterative improvements from feedback are critical for language models and reinforcement learning is the natural and right framework. A modular architecture is thus preferred, with reliable and valuable feedback and efficient algorithms.
Jing YANG
Zhejiang University
Dr. Jing YANG is a professor of psycholinguistics at Zhejiang University. Her research interests include bilingualism, second language learning, and language disabilities. In her research, she applies psycholinguistics and neurolinguistic approaches to examine the neurocognitive mechanisms underlying language learning and individual differences. Through these investigations, she aims to advance the understanding of the relationship between human brain plasticity and language learning.
Keynote Title
The Evolution of Neurocognitive Models of Second Language Learning
Keynote Abstract
More than half of the world’s population can use or speak more than one language. In the past 70 years, a number of verbal and computational models have been developed to account for the neurocognitive mechanism underlying bilingualism or second language learning. In this talk, I will review those models, along with their contributions and limitations. Recent trends in this booming area will then be presented. Finally, future possibilities based on interdisciplinary collaboration will be discussed.
Xingyi Zhang
Anhui University
Xingyi Zhang (Senior Member, IEEE) received the B.Sc. degree from Fuyang Normal College, Fuyang, China, in 2003, and the M.Sc. and Ph.D. degrees from Huazhong University of Science and Technology, Wuhan, China, in 2006 and 2009, respectively. He is currently a Professor with the School of Artificial Intelligence, Anhui University, Hefei, China. His current research interests include unconventional models and algorithms of computation, evolutionary multiobjective optimization, and complex network analysis. Dr. Zhang is the recipient of the 2018 and 2021 IEEE Transactions on Evolutionary Computation Outstanding Paper Award and the 2020 IEEE Computational Intelligence Magazine Outstanding Paper Award. He is an Associate Editor of the IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION.
Keynote Title
Evolutionary large-scale sparse multi-objective optimization
Keynote Abstract
In the past years, large-scale multi-objective optimization has become one of the hot topics in evolutionary computation community and a large number of works related to this topic have been reported, including benchmarks and evolutionary algorithms. In this talk, I will focus on a new class of large-scale multi-objective optimization, termed sparse large-scale multi-objective optimization. To be specific, I will first give some concepts related to evolutionary computation and large-scale multi-objective optimization. Then, I will introduce several recent works on evolutionary sparse large-scale multi-objective optimization.
