报告题目：Some Issues in Random Learning of Neural Networks

报告摘要：This talk presents some questionable issues in randomized learning techniques for feed-forward neural networks. The scope setting of random weights and biases plays a key role in approximation capability of nonlinear maps over compact sets. Unfortunately, some misleading results have been reported in literature and resulted in some misunderstandings on such type of learning techniques. Two counter examples are presented in this seminar to clarify the fact. This finding is significant to properly use the learning algorithm in applications.

报告人：王殿辉，博士

时 间：12月21日（周一）下午13：30—14：30

地 点：18-918（理学院会议室）

人物名片：

Dr Wang received his PhD degree in March 1995, from the School of Information Science and Engineering, NortheasternUniversity, Shenyang, China. From September 1995 to August 1997, he worked as a Postdoctoral Fellow at the School of Electronic and Electrical Engineering, Nanyang Technological University, Singapore. He then worked as a Research Associate and Research Fellow for three years until the end of June 2001 in the Department of Computing, The Hong Kong Polytechnic University, Hong Kong. Since July 2001, he has been with the Department of Computer Science and Computer Engineering at La Trobe University, Australia, and currently working in the same department as a Reader in Computer Science. Since 2010, Dr Wang has been an adjunct Professor in The State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China. Dr. Wang's working areas include data mining and computational intelligence systems for Bioinformatics, Information Retrieval and Engineering Applications. Technically, his research focus falls in subtle pattern discovery and recognition using neural networks and fuzzy systems, and recently he is interested in big data regression, classification and mining with applications using computational intelligence techniques. He is a Senior Member of IEEE, and serving as an Associate Editor for several international journals including IEEE Trans. On Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, INFORMATION SCIENCES, NEUROCOMPUTING, and a Subject Editor for APPLIED MATHEMATICAL MODELLING

欢迎广大师生参加!

半岛平台数学科学系