自适应多目独立成分分析  

Adaptive Independent Component Analysis under Multisensing

作　　者：佘堃[1] 蒲红梅[2] 郑方伟[1] 周明天[1] 

机构地区：[1]电子科技大学计算机科学与工程学院 [2]重庆通信学院第4系,重庆沙坪坝区400035

出　　处：《电子科技大学学报》2007年第1期11-13,共3页Journal of University of Electronic Science and Technology of China

摘　　要：通过分析LCNN的学习方程,发现Lagrange约束项的物理本质是有监督学习的下降速率,提出了自适应LCNN(ALCNN)算法,避开了病态矩阵的问题,并将学习矩阵和独立成分求解复杂性都降到了O(n)。In this paper, LCNN equation is investigated carefully and the inward nature of constraints, which was the down speed of supervised learning, is discovered. At the end, adaptive LCNN （ALCNN） is proposed, which not only can solve ill-conditioned matrix, but also the computing complexities of learning matrix and independent components are sympolied to O（n）.

关 键 词：独立成分分析 盲源分离系统 鸡尾酒会问题 

分 类 号：TN911.7[电子电信—通信与信息系统]