Plenary Speaker - ICIC 2021

ICIC 2021 Plenary Speakers

Anthony Cohn

C.L.Philip Chen

GuangRen Duan

DingGang Shen

	Anthony Cohn PhD & Professor Fellow of the Royal Academy of Engineering, AAAI Fellow, AISB Fellow, IET Fellow University of Leeds, England
	C.L.Philip Chen Ph.D & Professor Member of Academia Europaea, IEEE Fellow, AAAS Fellow, Editor in Chief, IEEE Transactions on Cybernetics South China University of Technology, China
	GuangRen Duan PhD & Professor Academician of the Chinese Academy of Sciences, IEEE Fellow, IET Fellow, CAA Fellow Southern University of Science and Technology, Shenzhen, China Harbin Institute of Technology, China
	DingGang Shen PhD & Professor IEEE Fellow, AIMBE Fellow, IAPR Fellow, MICCAI Fellow ShanghaiTech University, China

Learning about Language and Action for Robots

Anthony Cohn, PhD & Professor
Fellow of the Royal Academy of Engineering, AAAI Fellow, AISB Fellow, IET Fellow
Automated Reasoning in the School of Computing, University of Leeds, England

Abstract:To operate effectively, and to collaborate with humans, robots need to know much about the world, including the kinds of objects in the world, their properties, the spatial relationships between them and actions that can be performed on them, as well as how language is used to describe these things. I will present a cognitively plausible novel framework capable of incrementally learning a language used to give commands to a robot in a table top environment, and the grounding of linguistic concepts to the induced visual semantics of the observed scenes. The system also induces a set of probabilistic grammar rules governing the previously unknown language. I also plan to talk about new work in which we show how robots can improve their manipulation planning in cluttered environments by learning from human demonstrations in virtual worlds.

Bio-Sketch:Anthony Cohn is Professor of Automated Reasoning in the School of Computing, at the University of Leeds. His current research interests range from theoretical work on spatial calculi (receiving a KR test-of-time classic paper award in 2020) and spatial ontologies, to cognitive vision, grounding language to vision, robotics, modelling spatial information in the hippocampus, and Decision Support Systems, particularly for the built environment. He is Editor-in-Chief Spatial Cognition and Computation and was previously Editor-in-chief of the AI journal. He is the recipient of the 2015 IJCAI Donald E Walker Distinguished Service Award which honours senior scientists in AI for contributions and service to the field during their careers, as well as the 2012 AAAI Distinguished Service Award. He is a Fellow of the Royal Academy of Engineering, the Alan Turing Institute in the UK, and is also a Fellow of AAAI, AISB, EurAI (formerly ECCAI; Founding Fellow), the BCS, and the IET. He is a Distinguished Visiting Professor at Tongji University and Qingdao University of Science and Technology, and an Adjunct Professor at Shandong University.

A Dynamic Neural Network Structure and its Application for Continuous Learning in an Open Environment

C.L.Philip Chen, PhD & Professor
Member of Academia Europaea, IEEE Fellow, AAAS Fellow, IAPR Fellow
Editor in Chief, IEEE Transactions on Cybernetics
South China University of Technology, China

Abstract:Learning in neural networks suffers from the fixed structure of the network with a given number of layers and neurons when gather information for training. When the learning is unsatisfied, a new structure is re-designed and the process is repeated. In this talk, a dynamic neural network structure via Stacked Broad Learning Systems (BLS) will be discussed. The BLS has been proved to be effective and efficient lately. The proposed dynamic model is a novel incremental stacking of BLS. This invariant inherits the efficiency and effectiveness of BLS that the structure and weights of lower layers of BLS are fixed when the new blocks are added. The modified incremental stacking algorithm computes not only the connection weights between the new stacking blocks but also the connection weights of the enhancement nodes within the BLS block. Experimental results on UCI datasets, MNIST dataset, NORB dataset, CIFAR-10 dataset, SVHN dataset, and CIFAR-100 dataset indicate that the proposed method outperforms the other state-of-the-art methods on both accuracy and training speed, such as Deep Residual Networks. In addition, taking the advantages of BLS that can accumulate and reuse the learned knowledge, applications of BLS, Federated Broad Learning, in an open environment will be discussed. Federated Broad Learning supports learning from streaming data continuously, so it can adapt to the environment changes and provide better real-time performance. The broad learning enabled systems have been rigorously established in theory and tested in both simulation and experimental studies.

Bio-Sketch:C.L.Philip Chen (F’07) is the Chair Professor and Dean of the College of Computer Science and Engineering, South China University of Technology and was a Chair Professor of the Faculty of Science and Technology, University of Macau, where he was the former Dean (2010-2017). He is a Fellow of IEEE, AAAS, IAPR, CAA, and HKIE; a member of Academia Europaea (AE), European Academy of Sciences and Arts (EASA). He received IEEE Norbert Wiener Award in 2018 for his contribution in systems and cybernetics, and machine learnings. He was a recipient of the 2016 Outstanding Electrical and Computer Engineers Award from his alma mater, Purdue University. He received IEEE Transactions on Neural Networks and Learning Systems best transactions paper award two times for his papers in 2014 and 2018, Franklin Taylor best conference paper award in IEEE Int’l Conf. on SMC 2019. He is a highly cited researcher by Clarivate Analytics in 2018, 2019, and 2020. Currently, he is the Editor-in-Chief of the IEEE Transactions on Cybernetics after he completed his term as the Editor-in-Chief of the IEEE Transactions on Systems, Man, and Cybernetics: Systems (2014-2019). He was the IEEE Systems, Man, and Cybernetics Society President from 2012 to 2013, an Associate Editor of the IEEE Transactions on AI, IEEE Trans on SMC: Systems, and IEEE Transactions on Fuzzy Systems, an Associate Editor of China Sciences: Information Sciences. He received Macau FDCT Natural Science Award three times and a First-rank Guangdong Province Scientific and Technology Advancement Award in 2019. His current research interests include cybernetics, computational intelligence, and systems.

Fully actuated system approach for discrete-time systems

Center for Control Science and Technology
Academician of the Chinese Academy of Sciences, IEEE Fellow, IET Fellow, CAA Fellow
GuangRen Duan, PhD & Professor
The Southern University of Science and Technology, Shenzhen, China
Harbin Institute of Technology, China

Abstract:Physically, a fully actuated system is regarded to be a second-order mechanical system, which has a control actuator at each freedom. For such a system, a controller can be easily designed to cancel the nonlinearities in the system and thus a constant linear closed-loop system is resulted in. Unfortunately, this set of fully actuated systems, although possess such a superior advantage, have not attracted much attention of the control scientists, since they are generally considered to be only a very small minority of control systems. This physical world is governed by a series physical laws, including Newton's Law, Theorem of Linear and Angular Momentum, Lagrangian Equation, and Kirchhoff's Law of Voltage or Current. When modelling by such physical laws, the set of basic equations originally established are generally of second-order, and are often fully actuated. However, in state-space approaches, all these basic second-order equations are converted into first-order state-space models. Very recently, it is revealed that the physical concept of full actuation can be mathematically generalized to describe a variety of control systems, and most under-actuated systems can be converted into high-order fully actuated (HOFA) ones. This discovery motivates the very effective and simple HOFA approaches for control systems analysis and design. This talk presents a brief introduction to the proposed HOFA approaches, with an emphasis on the control of discrete-time systems.

Bio-Sketch:GuangRen Duan, received his Ph.D. degree in Control Systems Sciences from Harbin Institute of Technology, Harbin, P. R. China, in 1989. After a two-year post-doctoral experience at the same university, he became professor of control systems theory at that university in 1991. He is the founder and the Director of the Center for Control Theory and Guidance Technology at Harbin Institute of Technology, and recently he is also in charge of the Center for Control Science and Technology at the Southern University of Science and Technology. He is currently an Academician of the Chinese Academy of Sciences, and Fellow of CAA, IEEE and IET. His main research interests include parametric control systems design, nonlinear systems, descriptor systems, spacecraft control and magnetic bearing control. He is the author and co-author of 5 books and over 280 SCI indexed publications.

Integrating AI in Imaging, Quantification, and Identification of COVID-19

DingGang Shen, PhD & Professor
IEEE Fellow, AIMBE Fellow, IAPR Fellow, MICCAI Fellow
School of BME, ShanghaiTech University
Shanghai United Imaging Intelligence Co., Ltd.

Abstract:This talk will discuss how AI can be applied to imaging, quantification and identification of COVID-19. Specifically, for better clinical outcome, full-stack AI should be designed, starting from source (i.e., automated patient setup and fast imaging) to disease detection, follow-up, diagnosis, and outcome prediction in the whole clinical pipeline. The examples of how these full-stack AI can be fast developed and applied to contactless imaging of COVID-19, accurate delineation of lung infection, as well as identification of COVID-19 from other pneumonia and the predication of mild-to-severe conversion for COVID-19 patients are demonstrated in this talk. This imaging-based full-stack solution for COVID-19 also got SAIL Award in The World Artificial Intelligence Conference 2020.

Bio-Sketch:DingGang Shen is Professor and Dean of School of Biomedical Engineering, ShanghaiTech University, and also Co-CEO of United Imaging Intelligence (UII). He is Fellow of IEEE, Fellow of The American Institute for Medical and Biological Engineering (AIMBE), Fellow of The International Association for Pattern Recognition (IAPR), and also Fellow of The Medical Image Computing and Computer Assisted Intervention (MICCAI) Society. He was Jeffrey Houpt Distinguished Investigator, and (Tenured) Full Professor in the University of North Carolina at Chapel Hill (UNC-CH), directing The Center of Image Analysis and Informatics, The Image Display, Enhancement, and Analysis (IDEA) Lab, and The Medical Image Analysis Core. He was also a tenure-track Assistant Professor in the University of Pennsylvanian (UPenn) and a faculty member in the Johns Hopkins University. His research interests include medical image analysis, computer vision, and pattern recognition. He has published more than 1100 peer-reviewed papers in the international journals and conference proceedings, with H-index 113. He serves as Editor-in-Chief for Frontiers in Radiology, as well as editorial board member for eight international journals. Also, he has served in the Board of Directors, The Medical Image Computing and Computer Assisted Intervention (MICCAI) Society, in 2012-2015, and was General Chair for MICCAI 2019.