【韶风名家论坛】Convexity, Sparsity, Nullity and all that … in Machine Learning

报告题目:Convexity, Sparsity, Nullity and all that … in Machine Learning
主 讲 人:Hamid Krim,北卡罗来州立大学教授,IEEE Fellow 
 
报告人简介:
  Hamid Krim, 现任美国北卡罗来纳州立大学电子与计算机工程系教授,研究兴趣为统计信号和图像分析、应用问题的数学建模。Krim教授曾担任AT&T贝尔实验室、麻省理工大学研究专家;曾获贝尔实验室杰出成绩奖,美国国家科学基金会职业成就奖。目前,Krim是IEEE Transactions on Signal Processing的副主编IEEE Signal Processing Magazine的编委会成员,SPTM和Big Data Initiative的程序委会员会成员,2008年成为IEEE Fellow,被评为2015-2016年IEEE SP Society Distinguished Lecturer。
 
报告摘要:
  High dimensional data exhibit distinct properties compared to its low dimensional counterpart; this causes a common performance decrease and a formidable computational cost increase of traditional approaches. Novel methodologies are therefore needed to characterize data in high dimensional spaces.
  Considering the parsimonious degrees of freedom of high dimensional data compared to its dimensionality, we study the union-of-subspaces (UoS) model, as a generalization of thelinear subspace model. The UoS model preserves the simplicity of the linear subspace model, and enjoys the additional ability to address nonlinear data. We show a sufficient condition to use l1 minimization to reveal the underlying UoS structure, and further propose a bi-sparsity model (RoSure) as an effective algorithm, to recover the given data characterized by the UoS model from non-conforming errors/corruptions.
  As an interesting twist on the related problem of Dictionary Learning Problem, we discuss the sparse null space problem (SNS). Based on linear equality constraint, it first appeared in 1986 and hassince inspired results, such as sparse basis pursuit, we investigate its  relation to the analysis dictionary learning problem, and show that the SNS problem plays a central role, and may naturally be exploited  to solve dictionary learning problems.
  Substantiating examples are provided, and the application and performance of these approaches are demonstrated on a wide range of problems, such as face clustering and video segmentation.
 
主持人:欧阳建权教授,永利APP信息工程学院副院长
时 间:2017年3月30日下午2:00
地 点:工科楼北楼201
 
欢迎广大师生参加!
 
永利APP信息工程学院
智能计算与信息处理教育部重点实验室
2017年3月28日

上一条:【韶风名家论坛】Precise Tuning in the Surface and Interface of Metal Materials for Energy Electrocatalysis 下一条:【就业创业大讲堂】熊晓鸽、 陈小华—巅峰对话:漫谈创新与创业

关闭

分享到
相关链接
  • 信息公开
  • 图书馆
  • 人才招聘
  • 三翼校园
  • 教育基金会

版权所有 ? 永利APP. 地址:中国湖南湘潭. 邮编:411105
  (湘ICP备18021862号-2) 湘教QS3-200505-000059
湘公网安备 43030202001058号
   

XML 地图 | Sitemap 地图