报告题目：Stochastic Configuration Networks for Industrial Artificial Intelligence
报告摘要：Recently, we developed a new randomized learning algorithm and ensure the resulting model, termed Stochastic Configuration Networks (SCNs), holds the universal approximation property. Such a milestone progress greatly contributes to both the advancement of knowledge on randomized learning theory and the development of lightweight computing technology for IoT-based industrial applications. This presentation aims to introduce the state-of-the-art of SCN models, algorithms and applications to the instrument and control community.
报告人简介：Dr. Wang was awarded a Ph.D. from Northeastern University, Shenyang, China, in 1995. From 1995 to 2001, he worked as a Postdoctoral Fellow at Nanyang Technological University, Singapore, and a Researcher at The Hong Kong Polytechnic University, Hong Kong, China. From July 2001 to December 2020, he worked as a Reader in the Department of Computer Science and Information Technology, La Trobe University, Australia, and with adjunct appointment from 2021. Since 2017, Dr Wang has been a visiting Professor at State Key Laboratory of Synthetical Automation of Process Industries, also Industrial AI Research Institute, Northeastern University, China. In July 2021, He joined AI Research Institute at China University of Mining and Technology, working as a Dean, Professor, and Director of Research Center for Stochastic Configuration Machines. His current research focuses on industrial artificial intelligence, specifically on Deep Stochastic Configuration Networks (http://www.deepscn.com/) for data analytics in process industries, intelligent sensing, and control systems, prediction of significant and small probability events. Dr. Wang published more than 240 technical papers on applied mathematics, control engineering and computer sciences. Dr. Wang is a Senior Member of IEEE, serving as an Associate Editor for IEEE Transactions on Cybernetics, IEEE Transactions on Fuzzy Systems, Information Sciences, Artificial Intelligence Review and WIREs Data Ming and Knowledge Discovery.