报告题目：Lagrange Programming Neural Network for Sparse Approximation
主讲嘉宾：Prof. Chi-Sing Leung City University of Hong Kong
时间：2016年6月28日（星期二）10:30--11:30am
地点：深圳大学南区基础实验楼北座信息工程学院N710会议室
报告摘要:
The Largrange programming neural network approach provides a general framework for solving constrianed optimization problems. The major limitation of the LPNN approach is that the objective function and the constraints should be twice differentiable. Since sparse approximation involves non-differentiable functions, the original LPNN approach is not suitable for recovering sparse signals. This talk presents a new formulation of the LPNN approach based on the concept of the local competition algorithm (LCA) and subdifferential. Unlike the classical LCA approach which is able to solve unconstrained optimization problems only, the proposed LPNN approach is able to solve the constrained optimization problems in sparse approximation. Three problems in sparse approximation will be discussed in this talk. They are basis pursuit (BP), basis pursuit denoise (BPDN), and least absolute shrinkage and selection operator (LASSO).
嘉宾简介：
Chi Sing Leung received the PhD. degree in computer science from the Chinese University of Hong Kong in 1995. He is currently a Professor in the Department of Electronic Engineering, City University of Hong Kong. His research interests include neural computing and computer graphics. He has published over 120 journal papers in the areas of Digital Signal Processing, Neural Networks, and Computer Graphics. In 2005, he received the 2005 IEEE Transactions on Multimedia Prize Paper Award for his paper titled, “The Plenoptic Illumination Function”. He was a member of Organizing Committee of ICONIP2006. He was the Program Chair of ICONIP2009 and ICONIP2012. He is/was the guest editors of several journals, including Neural Computing and Applications, Neurocomputing, and Neural Processing Letters. From 2007 to 2015, He was a governing board member of the Asian Pacific Neural Network Assembly (APNNA) and Vice President of APNNA.
欢迎各位老师和同学参加。
