JULY 23-25, 2019 Shenyang, Liaoning, China
This talk provides a brief introduction to Reinforcement Learning (RL) technology, summarizes recent developments in this area, and discusses their potential applications to industrial decision making problems. The paper begins with a brief introduction to RL, a machine learning technology that allows an agent to learn, through trial and error, the best way to accomplish a task. We then highlight two new developments in RL that have led to the recent wave of applications and media interest. A comparison of the key features of RL vs. Model Predictive Control (MPC) and other traditional mathematical programming based methods is then presented in order to clarify their relative merits and shortcomings. This is followed by an assessment of areas that RL technology can potentially be used in industrial decision-making problems. Particular focus is given on integrating capacity planning, production planning and scheduling layers in multi-scale, multi-period, stochastic environments.
Sparse modelling is a particular manifestation of this principle of parsimony; it is one of the ways to realize “simple models”. In this talk, first I shall discuss very briefly a few illustrative approaches to classical sparse modeling in statistical learning and then talk about some of the attempts using the computational intelligence framework, in particular with neural networks and fuzzy systems. In this context, I shall consider three types of problems, classification, clustering and regression. Finally, I shall consider how we can achieve sparse modelling with a control on the level of redundancy in the system.
Jay H. Lee obtained his B.S. degree in Chemical Engineering from the University of Washington, Seattle, in 1986, and his Ph.D. degree in Chemical Engineering from California Institute of Technology, Pasadena, in 1991. From 1991 to 1998, he was with the Department of Chemical Engineering at Auburn University, AL, as an Assistant Professor and an Associate Professor. From 1998-2000, he was with School of Chemical Engineering at Purdue University, West Lafayette, and then with the School of Chemical Engineering at Georgia Institute of Technology, Atlanta from 2000-2010. Since 2010, he is with the Chemical and Biomolecular Engineering Department at Korea Advanced Institute of Science and Technology (KAIST), where he was the department head from 2010-2015. He is currently a Professor, Associate Vice President of International Office, and Director of Saud Aramco-KAIST CO2 Management Center at KAIST. He has held visiting appointments at E. I. Du Pont de Numours, Wilmington, in 1994 and at Seoul National University, Seoul, Korea, in 1997. He was a recipient of the National Science Foundation’s Young Investigator Award in 1993 and was elected as an IEEE Fellow and an IFAC (International Federation of Automatic Control) Fellow in 2011 and AIChE Fellow in 2013. He was also the recipient of the 2013 Computing in Chemical Engineering Award given by the AIChE’s CAST Division and the 2016 Roger Sargent Lecturer at Imperial College, UK. He is currently an Editor of Computers and Chemical Engineering and also the chair of IFAC Coordinating Committee on Process and Power Systems. He published over 180 manuscripts in SCI journals with more than 13000 Google Scholar citations. His research interests are in the areas of system identification, state estimation, robust control, model predictive control, and reinforcement learning with applications to energy systems, bio-refinery, and CO2 capture/conversion systems.
Abstract：Deep learning is a hot topic during the past few years. Generally, the word "deep learning" is regarded as a synonym of "deep neural networks (DNNs)". In this talk, we will discuss on essentials in deep learning and claim that deep learning is not necessarily to be realized by neural networks. We will then present an exploration to non-NN style deep learning, where the building blocks are non-differentiable modules and the training process does not rely on backpropagation or gradient-based adjustment.
Zhi-Hua Zhou is a Professor of Nanjing University, China. He is the Head of the Department of Computer Science and Technology, Dean of the School of Artificial Intelligence, and Founding Director of the LAMDA Group. His main research interests are in artificial intelligence, machine learning and data mining. He authored the books "Ensemble Methods: Foundations and Algorithms (2012)" and "Machine Learning (in Chinese, 2016)", and published more than 200 papers in top-tier international journals/conferences. According to Google Scholar, his publications have received more than 40,000 citations, with an H-index of 92. He also holds 24 patents and has rich experiences in industrial applications. He has received various awards, including the IEEE Computer Society Edward J. McCluskey Technical Achievement Award, PAKDD Distinguished Contribution Award, IEEE ICDM Outstanding Service Award, National Natural Science Award of China, etc. He serves as the Editor-in-Chief of Frontiers of Computer Science, Associate Editor-in-Chief of Science China Information Sciences, and Action/Associate Editor of Machine Learning, IEEE PAMI, ACM TKDD, etc. He founded ACML (Asian Conference on Machine Learning) and served as Chair for many prestigious conferences, such as Program Chair of AAAI 2019, General Chair of IEEE ICDM 2016, Program Chair of IJCAI 2015 Machine Learning track, etc. He is the Chair of CCF-AI, and was Chair of the IEEE Computational Intelligence Society Data Mining Technical Committee. He is a foreign member of the Academy of Europe, and a Fellow of the ACM, AAAI, AAAS, IEEE, IAPR, IET/IEE, CCF, and CAAI.
Abstract: This talk presents a few recent advances in data driven evolutionary optimization. We begin with Bayesian approaches to high dimensional multi-objective optimization of high dimensional problems, followed by knowledge transfer and selective ensemble strategies in offline data driven optimization. Application examples in aerodynamic optimization and industrial processes will be given.
Yaochu Jin received the B.Sc., M.Sc., and Ph.D. degrees from Zhejiang University, Hangzhou, China, in 1988, 1991, and 1996, respectively, and the Dr.-Ing. degree from Ruhr University Bochum, Germany, in 2001.
He is currently a Distinguished Chair Professor in Computational Intelligence, Department of Computer Science, University of Surrey, Guildford, U.K., where he heads the Nature Inspired Computing and Engineering Group. He was a Finland Distinguished Professor funded by the Finnish Funding Agency for Innovation (Tekes) and a Changjiang Distinguished Visiting Professor appointed by the Ministry of Education, China. His main research interests include data-driven surrogate-assisted evolutionary optimization, evolutionary learning, interpretable and secure machine learning, and evolutionary developmental systems. His research has been funded by EU, EPSRC, Royal Society, NSFC, and the industry, including Honda, Airbus, and Bosch.
Dr Jin is the Editor-in-Chief of the IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS and Co-Editor-in-Chief of Complex & Intelligent Systems. He is an IEEE Distinguished Lecturer (2013-2015 and 2017-2019) and past Vice President for Technical Activities of the IEEE Computational Intelligence Society (2014-2015). He is the recipient of the 2018 IEEE Transactions on Evolutionary Computation Outstanding Paper Award, and the 2015 and 2017 IEEE Computational Intelligence Magazine Outstanding Paper Award. He is an IEEE Fellow.
|Submission of draft p|