Recurrent Neural Network Approach Based on the Integral Representation of the Drazin Inverse

被引:52
作者
Stanimirovic, Predrag S. [1 ]
Zivkovic, Ivan S. [2 ]
Wei, Yimin [3 ,4 ]
机构
[1] Univ Nis, Fac Sci & Math, Visegradska 33, Nish 18000, Serbia
[2] Serbian Acad Arts & Sci, Math Inst, Beograd 11001, Serbia
[3] Fudan Univ, Sch Math Sci, Shanghai 200433, Peoples R China
[4] Fudan Univ, Key Lab Math Nonlinear Sci, Shanghai 200433, Peoples R China
基金
中国国家自然科学基金;
关键词
GENERALIZED INVERSE; ZNN MODELS; EQUATIONS; ZFS;
D O I
10.1162/NECO_a_00771
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this letter, we present the dynamical equation and corresponding artificial recurrent neural network for computing the Drazin inverse for arbitrary square real matrix, without any restriction on its eigenvalues. Conditions that ensure the stability of the defined recurrent neural network as well as its convergence toward the Drazin inverse are considered. Several illustrative examples present the results of computer simulations.
引用
收藏
页码:2107 / 2131
页数:25
相关论文
共 38 条
[1]  
Abadir K. M., 2005, MATRIX, V1
[2]  
[Anonymous], 1988, PROC NEURAL INF PROC
[3]  
Ben-Israel A., 2003, Generalized inverses: theory and applications
[4]   APPLICATIONS OF DRAZIN INVERSE TO LINEAR-SYSTEMS OF DIFFERENTIAL EQUATIONS WITH SINGULAR CONSTANT COEFFICIENTS [J].
CAMPBELL, SL ;
MEYER, CD ;
ROSE, NJ .
SIAM JOURNAL ON APPLIED MATHEMATICS, 1976, 31 (03) :411-425
[5]  
Campbell SL, 2009, GEN INVERSES LINEAR
[6]   On integral representations of the Drazin inverse in Banach algebras [J].
Castro-González, N ;
Koliha, JJ ;
Wei, YM .
PROCEEDINGS OF THE EDINBURGH MATHEMATICAL SOCIETY, 2002, 45 :327-331
[7]   Unified stabilization approach to principal and minor components extraction algorithms [J].
Chen, TP ;
Amari, S .
NEURAL NETWORKS, 2001, 14 (10) :1377-1387
[8]   Global convergence of Oja's subspace algorithm for principal component extraction [J].
Chen, TP ;
Hua, YB ;
Yan, WY .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (01) :58-67
[9]  
Cichocki A., 1992, Bulletin of the Polish Academy of Sciences. Technical Sciences, V40, P387
[10]  
Golub G. H., 1996, MATRIX COMPUTATIONS