Keynote Speakers
(listed by last name alphabetically)
Tianyou Chai
IEEE Life Fellow
Northeastern University, China
Title
Intelligent Decision and Control Integrating System Based on End-edge-cloud Collaboration
端边云协同的智能决策与控制一体化系统
Abstract
To address the challenges hat online optimization of operational decision-making and control in complex industrial systems cannot be realized, this talk proposes a unified structure and algorithm for integrated operational optimization of decision-making and control, by combining control, optimization, and prediction with AI technology. It also proposed a parameter self-optimizing and self-learning algorithm for operational decision-making and control integrating systems, by combining mechanism analysis with deep learning, and digital twin with reinforcement learning. Based on the tight conjoining of and coordination between the end-edge-cloud collaboration technology of Industrial Internet and PLC control system, an intelligent decision-making and control integrating system based on end-edge-cloud collaboration is developed. The system includes the end serving as an actual operational optimization decision-making and control system at the industrial site, as well as a cloud-edge collaborative parameter self-learning and self-optimizing system in digital space that operates in coordination with the end. The system has been successfully applied in the energy intensive equipment—fused magnesium furnace and achieved remarkable results in the reduction of carbon emission.
本报告针对复杂工业系统运行决策与控制无法在线优化的挑战难题，将控制、优化与预测和AI技术相结合，提出了运行优化决策与控制一体化的统一结构和算法。机理分析与深度学习、数字孪生与强化学习相结合，提出了优化决策与控制一体化系统参数自优化自学习算法。将工业互联网端边云协同技术和PLC管理控制系统深度融合与协同，研发了端边云协同的优化决策与控制一体化智能系统，包括端的实际优化运行决策与控制系统和数字空间的与端系统协同运行的云边协同参数自学习自优化系统。该系统成功应用于重大耗能设备—电熔镁炉，取得低碳运行的显著效果。
Biography
Tianyou Chai received the Ph.D. degree in control theory and engineering in 1985 from Northeastern University, Shenyang, China, where he became a Professor in 1988. He is the founder and Director of the Center of Automation, which became a National Engineering and Technology Research Center and a State Key Laboratory. He is a member of Chinese Academy of Engineering, IFAC Fellow and IEEE Fellow. He has served as director of Department of Information Science of National Natural Science Foundation of China from 2010 to 2018.
His current research interests include modeling, control, optimization and integrated automation and intelligence of complex industrial processes.
He has published 397 peer reviewed international journal papers，including 273 IEEE&IFAC papers. His paper titled Hybrid intelligent control for optimal operation of shaft furnace roasting process was selected as one of three best papers for the Control Engineering Practice Paper Prize for 2011-2013. He has developed control technologies with applications to various industrial processes. For his contributions, he has won 5 prestigious awards of National Natural Science, National Science and Technology Progress and National Technological Innovation, the 2007 Industry Award for Excellence in Transitional Control Research from IEEE Multiple-conference on Systems and Control, and the 2017 Wook Hyun Kwon Education Award from Asian Control Association.
Wolfgang Maass
Graz University of Technology, Austria
Title
New ingredients for brain-inspired AI
Abstract
I will discuss some recently discovered brain mechanisms that suggest new brain-inspired AI approaches to planning, problem solving, binding, and compositional computing. This was elucidated in recent collaborations with very talented junior researchers from China. Details can be found in our first publications on these results:
Chen, G., Scherr, F., & Maass, W. (2023). Data-based large-scale models provide a window into the organization of cortical computations. bioRxiv
Stöckl, C., Yang, Y., & Maass, W. (2024). Local prediction-learning in high-dimensional spaces enables neural networks to plan. Nature Communications
Wu, Y., & Maass, W. (2025). A simple model for Behavioral Time Scale Synaptic Plasticity (BTSP) provides content addressable memory with binary synapses and one-shot learning. Nature Communications
Yu, C., Wu, Y., Wang, A., & Maass, W. (2025). Behavioral Time Scale Synaptic Plasticity (BTSP) endows Hyperdimensional Computing with attractor features. bioRxiv
Lin, H., Yang, Y., Zhao, R., Pezzulo, G., & Maass, W. (2025). Neural sampling from cognitive maps supports goal-directed imagination and planning. bioRxiv
Biography
Phd in Mathematics at the Ludwig-Maximilians-Universitaet in Munich.
1979 - 1984 research at MIT, the University of Chicago, and the University of California at Berkeley as Heisenberg-Fellow of the Deutsche Forschungsgemeinschaft.
1982 - 1986 Associate Professor and 1986 - 1993 Professor of Computer Science at the University of Illinois in Chicago.
Since 1991 Professor of Computer Science at the Graz University of Technology in Austria.
Sloan Fellow at the Computational Neurobiology Lab of the Salk Institute (La Jolla, USA) during 1997/98.
2002/3 and 2012 Visiting Professor at the Brain-Mind Institute, EPFL, Lausanne, Switzerland.
Since 2005 Adjunct Fellow of the Frankfurt Institute of Advanced Studies
(FIAS)
2008 - 2012 Member of the Board of Governors of the International Neural Network Society.
Since 2013 Member of the Academia Europaea
2018: Co-Organizer of the Special Semester "The Brain and Computation" at the Simons Institute, University of California at Berkeley Since 2023: ELLIS Fellow, and Director of the ELLIS unit Graz (ELLIS = European Lab for Learning and Intelligent Systems)
Xin Yao
IEEE Fellow
Lingnan University, Hong Kong SAR, China
Title
Explaining Explainable Artificial Intelligence (XAI)
Abstract
Explainable Artificial Intelligence (XAI) has been a hot topic in recent years. Many papers and books have been published by researchers and practitioners from different communities, addressing different aspects of XAI. However, different papers seem to focus on different definitions of explainability. It is not entirely clear what XAI really means. Firstly, this talk will try to clarify what XAI actually means to different people, at different times and for different purposes. In other words, the talk will first put XAI in a four dimensional space and characterise it in terms of explaining to whom, when, what and how. Secondly, after identifying the most popular XAI technique --- feature attribution explanation (FAE), we will illustrate how evolutionary multi-objective optimisation could be used naturally to enhance explainability of machine learning models. Thirdly, in the opposite direction, we will demonstrate how XAI techniques can be used to enhance the performance of evolutionary algorithms. There are interesting synergies between XAI and evolutionary computation techniques. Finally, this talk ends with some concluding remarks and future research directions.
Biography
Xin Yao is the Vice President (Research and Innovation) and the Tong Tin Sun Chair Professor of Machine Learning at Lingnan University, Hong Kong SAR. He is an IEEE Fellow and was a Distinguished Lecturer of the IEEE Computational Intelligence Society (CIS). He served as the President (2014-15) of IEEE CIS and the Editor-in-Chief (2003-08) of IEEE Transactions on Evolutionary Computation. His major research interests include evolutionary computation, neural network ensembles, and multi-objective learning. His recent interests include online learning, class imbalance learning and trustworthy artificial intelligence. His work won the 2001 IEEE Donald G. Fink Prize Paper Award; 2010, 2016 and 2017 IEEE Transactions on Evolutionary Computation Outstanding Paper Awards; 2011 IEEE Transactions on Neural Networks Outstanding Paper Award; 2010 BT Gordon Radley Award for Best Author of Innovation (Finalist); and many other best paper awards at conferences. He received the 2012 Royal Society Wolfson Research Merit Award, the 2013 IEEE CIS Evolutionary Computation Pioneer Award, and the 2020 IEEE Frank Rosenblatt Award.