Dual systems for minor and principal component computation

被引:2
作者
Hasan, Mohammed A. [1 ]
机构
[1] Univ Minnesota, Dept Elect & Comp Engn, Duluth, MN 55812 USA
来源
2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12 | 2008年
关键词
principal components; minor components; generalized eigenvalue problem; Lyapunov stability; global convergence; Oja's learning rule; Rayleigh quotient; dual-purpose MCA/PCA systems;
D O I
10.1109/ICASSP.2008.4518006
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Converting principal component dynamical system to a minor component dynamical system and vice versa sometimes leads to unstable systems. In this paper, classes of globally stable dynamical systems that can be converted between PCA and MCA systems by merely switching the signs of some terms of a given system are developed. These systems axe shown to be applicable to symmetric and nonsymmetric matrices. These systems are then modified to be asymptotically stable by adding a penalty term. The proposed systems may apply to both the standard and the generalized eigenvalue problems. Lyapunov stability theory and LaSalle invariance principle are used to derive invariant sets for these systems.
引用
收藏
页码:1901 / 1904
页数:4
相关论文
共 9 条
[1]   Unified stabilization approach to principal and minor components extraction algorithms [J].
Chen, TP ;
Amari, S .
NEURAL NETWORKS, 2001, 14 (10) :1377-1387
[2]   The MCA EXIN neuron for the minor component analysis [J].
Cirrincione, G ;
Cirrincione, M ;
Hérault, J ;
Van Huffel, S .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (01) :160-187
[3]  
Khalil HK., 2002, NONLINEAR SYSTEMS, V3rd edition
[4]  
LaSalle J., 1960, IRE T CIRCUIT THEORY, V7, P520, DOI [10.1109/TCT.1960.1086720, DOI 10.1109/TCT.1960.1086720]
[5]  
Manton JH, 2003, 42ND IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-6, PROCEEDINGS, P1863
[6]   PRINCIPAL COMPONENTS, MINOR COMPONENTS, AND LINEAR NEURAL NETWORKS [J].
OJA, E .
NEURAL NETWORKS, 1992, 5 (06) :927-935
[7]   OPTIMAL UNSUPERVISED LEARNING IN A SINGLE-LAYER LINEAR FEEDFORWARD NEURAL NETWORK [J].
SANGER, TD .
NEURAL NETWORKS, 1989, 2 (06) :459-473
[8]   LEAST MEAN-SQUARE ERROR RECONSTRUCTION PRINCIPLE FOR SELF-ORGANIZING NEURAL-NETS [J].
XU, L .
NEURAL NETWORKS, 1993, 6 (05) :627-648
[9]  
[No title captured]