Complex recurrent neural network for computing the inverse and pseudo-inverse of the complex matrix

被引：45
作者：
Song, JY
Yam, Y [1 ]
机构：
[1] Chinese Univ Hong Kong, Dept Mech & Automat Engn, Shatin, NT, Peoples R China
[2] Chinese Univ Hong Kong, Dept Syst Engn & Engn Management, Shatin, NT, Peoples R China
来源：
APPLIED MATHEMATICS AND COMPUTATION | 1998年 / 93卷 / 2-3期
关键词：
recurrent neural network; complex neural network; matrix inversion;
D O I：
10.1016/S0096-3003(97)10064-9
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
A complex recurrent neural network (CRNN) is formulated and applied to compute the complex matrix inverse in real time. Both full rank and rank deficient matrices are considered. This paper extends recent works which apply real recurrent neural networks for rear-valued matrix inversion. (C) 1998 Elsevier Science Inc. All rights reserved.
引用
收藏
页码：195 / 205
页数：11
相关论文
共 12 条
[1]   ON THE COMPLEX BACKPROPAGATION ALGORITHM [J].
BENVENUTO, N ;
PIAZZA, F .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (04) :967-968
[2]  
CHEN CT, 1984, LINEAR SYSTEM THEORY, P400
[3]  
HIROSE A, 1992, P INT JOINT C NEUR N, V4, P152
[4]  
JANG J, 1988, NEURAL INFORM PROCES, P397
[5]   OUTPUT BEAM FOCUSABILITY OF A ND-GLASS ZIG-ZAG SLAB LASER [J].
KIM, BT ;
OISHIBASHI, Y ;
KANABE, T ;
NAKATSUKA, M ;
NAKAI, S .
IEEE PHOTONICS TECHNOLOGY LETTERS, 1990, 2 (01) :27-28
[6]  
LUO FL, 1992, APPL MATH COMPUT, V47, P109, DOI 10.1016/0096-3003(92)90040-8
[7]  
NITTA T, 1993, P 1993 INT JOINT C N, P1649
[8]  
SONG J, 1996, P 1996 IEEE INT C NE, V4, P2266
[9]   RECURRENT NEURAL NETWORKS FOR SOLVING SYSTEMS OF COMPLEX-VALUED LINEAR-EQUATIONS [J].
WANG, J .
ELECTRONICS LETTERS, 1992, 28 (18) :1751-1753
[10]   A RECURRENT NEURAL NETWORK FOR REAL-TIME MATRIX-INVERSION [J].
WANG, J .
APPLIED MATHEMATICS AND COMPUTATION, 1993, 55 (01) :89-100
12