Biography: Guang Ren, male, born in 1952, Received his doctoral degree in Control Engineering from Norwegian University of Science and Technology, professor of Dalian Maritime University, and former Dean of Marine Engineering College of Dalian Maritime University. In 2008 and 2003, it was ranked first in the second prize of Science and Technology Progress of Liaoning Province.
Title of Speech: Nature of scientific problems
Abstract: All scientific research must be aimed at scientific problems. So getting the scientific questions right is crucial. As Einstein said, "formulation of a new problem is often more essential than its solution, which may be merely a matter of mathematical or experimental skill, but to propose a new problem, a new possibility, to look at an old problem from a new Angle, requires creative imagination, and marks the true progress of science." From the perspective of philosophy of science, this talk explains the nature of scientific problems and discusses the methods of raising scientific problems. Take Einstein, Zhenning, Yang, Bill Gates, Feifei Li and the father of AlphaGo as examples to see how they reveal their scientific problems.
Biography: Leszek Rutkowski received the M.Sc., Ph.D., and D.Sc. degrees from the Wrocław University of Technology, Wrocław, Poland, in 1977, 1980, and 1986, respectively, and the Honoris Causa degree from the AGH University of Science and Technology, Kraków, Poland, in 2014. He is with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland, and with the Institute of Computer Science, AGH University of Science and Technology, Krakow, Poland, in both places serving as a professor. He is an Honorary Professor of the Czestochowa University of Technology, Poland, and he also cooperates with the University of Social Sciences in Łódź, Poland. From 1987 to 1990, he held a visiting position with the School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK, USA. His research interests include data stream mining, big data analysis, neural networks, agent systems, fuzzy systems, image processing, pattern classification, and expert systems. He has published more than 300 technical papers, including more than 40 in various series of IEEE Transactions. He is the president and founder of the Polish Neural Networks Society. He organized and served as a General Chair of the International Conferences on Artificial Intelligence and Soft Computing held in the period 1995 -2022. He is on the editorial board of several most prestigious international journals. He is a recipient of the IEEE Transactions on Neural Networks 2005 Outstanding Paper Award. He served in the IEEE Computational Intelligence Society as the chair of the Distinguished Lecturer Program (2008-2009) and the Standards Committee (2006-2007). He is the founding chair of the Polish chapter of the IEEE Computational Intelligence Society, which won the 2008 Outstanding Chapter Award. In 2004, he was awarded the IEEE Fellow membership grade for contributions to neurocomputing and flexible fuzzy systems. He received a degree honoris causa from the prestigious AGH University of Science and Technology in Cracow “in recognition of outstanding scientific achievements in the field of artificial intelligence - in particular, neuro-fuzzy systems.” He is a Full Member (Academician) of the Polish Academy of Sciences, elected in 2016, and a Member of the Academia Europaea, elected in 2022.
Title of Speech: Stream Data Mining: From Sliding Windows to Deep Learning
Abstract: This lecture presents a collection of original methods and algorithms for stream data mining. Unlike the vast majority of previous approaches, which are largely based on heuristics, it highlights methods and algorithms that are mathematically justified. First, the basic concepts of stream data mining are outlined with a special emphasis put on concept drift – the phenomenon describing the time-varying nature of streaming data. Next, it describes how to adapt static decision trees to accommodate data streams; in this regard, new splitting criteria are developed to guarantee that they are asymptotically equivalent to the classical batch tree. Moreover, new decision trees are designed, leading to the original concept of hybrid trees. In turn, nonparametric techniques based on Parzen kernels and orthogonal series are employed to address concept drift in the problem of non-stationary regressions and classification in a time-varying environment. Next, an extremely challenging problem that involves designing ensembles and automatically choosing their sizes is described and solved. Finally, it will be shown how to use Restricted Boltzmann Machines for stream data processing and monitoring.
Biography: Professor Yong-Duan Song is a Fellow of IEEE, Fellow of AAIA, Fellow of International Eurasian Academy of Sciences, and Fellow of Chinese Automation Association. He was one of the six Langley Distinguished Professors at National Institute of Aerospace (NIA), USA and register professional engineer (USA). He is currently the dean of Research Institute of Artificial Intelligence at Chongqing University. Professor Song is the Editor-in-Chief of IEEE Transactions on Neural Networks and Learning Systems (TNNLS) and the founding Editor-in-Chief of the International Journal of Automation and Intelligence.
Title of Speech: Neural Networks Driven Control Design and Analysis
Abstract: Neural networks and related learning algorithms are crucial components of artificial intelligence. The utilization of neural networks combined with learning algorithms for controller design has become a mainstream direction in the field of intelligent control. This talk will examine the typical NN driven design approaches and expose several critical issues related to functionality and effectiveness of the NN based control methods.
Biography: Kay Chen Tan is currently a Chair Professor (Computational Intelligence) of the Department of Computing, The Hong Kong Polytechnic University. He has co-authored 9 books and published over 300 peer-reviewed journal articles. Prof. Tan is currently the Vice-President (Publications) of IEEE Computational Intelligence Society, USA. He was the Editor-in-Chief of IEEE Transactions on Evolutionary Computation from 2015-2020 and IEEE Computational Intelligence Magazine from 2010-2013. Prof. Tan is an IEEE Fellow and an Honorary Professor at University of Nottingham in UK. He also serves as the Chief Co-Editor of Springer Book Series on Machine Learning: Foundations, Methodologies, and Applications.
Title of Speech: Towards Next-Generation Evolutionary Computation: Some Reflections
Abstract: Evolutionary computation refers to a set of stochastic search methods inspired by the principles of natural selection and genetics. It has demonstrated strong search capability in various applications, ranging from engineering design to financial forecasting and beyond. However, despite their success in some domains, there are several limitations when it comes to solving real-world search problems with high dimensionality, such as computational complexity, lack of robustness, and limited scalability.
It is known that deep machine learning has achieved remarkable breakthroughs in recent years, largely driven by rapid advancements in computing resources, the availability of big data, and the development of advanced algorithms. By learning from the success of deep machine learning, it is believed that the next generation of evolutionary algorithms should also leverage the availability of high-performance computing resources and other technologies to address the challenges of real-world problems. These algorithms should be more flexible, adaptive, and efficient, allowing them to provide optimal search solutions in a shorter amount of time.
In this talk, I will provide an overview of optimization in practical applications and delve into the reasons behind developing the next generation of evolutionary algorithms. Specifically, I will introduce our research on evolutionary transfer optimization, where we focus on creating distributed, scalable, and learnable evolutionary algorithms to tackle challenging optimization problems.
Biography:
Dongrui Wu (IEEE Fellow) received a B.E in Automatic Control from the University of Science and Technology of China, Hefei, China, in 2003, an M.Eng in Electrical and Computer Engineering from the National University of Singapore in 2006, and a PhD in Electrical Engineering from the University of Southern California, Los Angeles, CA, in 2009. He is now Professor and Deputy Director of the Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.
Prof. Wu's research interests include brain-computer interface, machine learning, computational intelligence, and affective computing. He has more than 200 publications (11000+ Google Scholar citations; h=57). He received the IEEE Computational Intelligence Society (CIS) Outstanding PhD Dissertation Award in 2012, the IEEE Transactions on Fuzzy Systems Outstanding Paper Award in 2014, the IEEE Systems, Man and Cybernetics (SMC) Society Early Career Award in 2017, the USERN Prize in Formal Sciences in 2020, the IEEE Transactions on Neural Systems and Rehabilitation Engineering Best Paper Award in 2021, the Chinese Association of Automation Early Career Award in 2021, and the Ministry of Education Young Scientist Award in 2022. His team won National Champion of the China Brain-Computer Interface Competition in two successive years (2021-2022). Prof. Wu is the Editor-in-Chief of IEEE Transactions on Fuzzy Systems.
Title of Speech: Efficient Optimization of TSK Fuzzy Systems
Abstract: TSK fuzzy systems have been widely used in classification and regression. However, when the training set is very large, traditional evolutionary algorithm based optimization and gradient descent based optimization may have prohibitive computational cost. This talk first introduces the functional equivalence/similarity between TSK fuzzy systems and some classical machine learning models, including radial basis function networks, mixture of experts, stacking and CART, and then extends efficient training algorithms for deep neural networks, e.g., mini-batch gradient descent, DropOut, batch normalization, Adam, etc., to the training of TSK fuzzy systems, for better generalization.
Biography:
Shen Yin (Fellow, IEEE) holds an M.Sc. in control and information systems and a Ph.D. (Dr.-Ing.) in electrical engineering and information technology from the University of Duisburg-Essen, Germany. He is currently a DNV Endowed Full Professor at the Department of Mechanical and Industrial Engineering, Norwegian University of Science and Technology, Norway. With research interests encompassing Fault diagnosis/prognosis and fault tolerance, Reliability, safety, and security, Data-driven monitoring and optimization, System and control theory, and Applications in health diagnosis and cyber-physical systems, he is actively engaged in advancing the field of industrial engineering.
In addition to his academic roles, he also holds editorial positions, including Co Editor-in-Chief of IEEE Transactions on Industrial Informatics, Deputy Editor-in-Chief of Discover Artificial Intelligence (Springer Nature), and serves as an Associate Editor for the IEEE Transactions on Industrial Electronics, IEEE Transactions on Consumer Electronics, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Industrial Cyber Physical Systems, and IEEE Journal of Emerging and Selected Topics in Industrial Electronics, etc.
He has been recognized for his contributions to the field, having received the NAMUR Award for "Process Automation" in 2012, the Best Paper Award from the IEEE Transactions on Industrial Electronics in 2015, and the China Youth Science and Technology Award in 2020, among other accolades. He has been consecutively listed as a Highly Cited Researcher by Clarivate from 2016 to 2022.
Title of Speech: Active and Passive Safety Considerations in Technical Processes
Abstract: In the quest for promoting sustainability in the realm of technological processes, safety emerges as a central focus. This overarching concern naturally divides into two key areas: passive diagnostics and active prognostics. Recent research endeavors have predominantly concentrated on developing safety strategies and proactively predicting the remaining useful life of technical processes and their components. This burgeoning body of research can be further classified into three methodological approaches: model-based, data-driven, and hybrid methodologies that amalgamate elements from both paradigms. Model-based approaches are lauded for their robust theoretical foundations and high interpretability, whereas data-driven methodologies exhibit their efficacy in scenarios where a comprehensive system model remains elusive. However, data-driven approaches are not without their intricacies, encompassing challenges such as data scarcity, robustness, sensitivity considerations, and the pressing need for seamless information integration. In pursuit of a comprehensive understanding, this presentation will also feature an extensive case study, elucidating a methodology for predicting residual useful life that seamlessly integrates both data and model-based approaches. Through this multifaceted exposition, we aim to provide a holistic perspective on the evolving landscape of proactive safety considerations in technical processes.