Improved Zhang neural network model and its solution of time-varying generalized linear matrix equations

被引:45
作者
Li, Zhan [1 ]
Zhang, Yunong [1 ]
机构
[1] Sun Yat Sen Univ, Sch Informat Sci & Technol, Guangzhou 510006, Guangdong, Peoples R China
关键词
Artificial neural networks; Time-varying; Generalized linear matrix equations (GLME); Activation functions; SOLVING ONLINE; IMPLEMENTATION; CONVERGENCE; STABILITY; SYSTEM; BP;
D O I
10.1016/j.eswa.2010.04.007
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 paper, a class of Zhang neural networks (ZNNs) are developed and analyzed on convergence properties. Different from conventional gradient-based neural networks (GNNs), such ZNN is designed based on the idea of measuring the time-derivation information of time-varying coefficients. The general framework of such a ZNN, together with its variant forms, is presented and investigated. The resultant ZNN model activated by linear functions possesses global exponential convergence to the time-varying equilibrium point. By employing proposed new smooth nonlinear odd-monotonically increasing activation functions, superior convergence could be achieved. Computer-simulation examples substantiate the efficacy of such a ZNN model in the context of solution of time-varying generalized linear matrix equations. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:7213 / 7218
页数:6
相关论文
共 30 条
[1]  
ARNOLD CP, 1983, IEEE T COMPUT, V32, P265, DOI 10.1109/TC.1983.1676218
[2]   Gradient based iterative algorithms for solving a class of matrix equations [J].
Ding, F ;
Chen, TW .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2005, 50 (08) :1216-1221
[3]   Mutual complement between statistical and neural network approaches for rock magnetism data analysis [J].
Guo, William W. ;
Li, Michael M. ;
Whymark, Gregory ;
Li, Zheng-Xiang .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (06) :9678-9682
[4]  
Hartman P, 1982, Ordinary differential equations, VSecond
[5]  
HERNANDEZ V, 1994, IEEE DECIS CONTR P, P449, DOI 10.1109/CDC.1994.410885
[6]   A digital hardware pulse-mode neuron with plecewise linear activation function [J].
Hikawa, H .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (05) :1028-1037
[7]   Feedforward neural network implementation in FPGA using layer multiplexing for effective resource utilization [J].
Himavathi, S. ;
Anitha, D. ;
Muthuramalingam, A. .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (03) :880-888
[8]  
Horn RA., 2013, MATRIX ANAL
[9]   Hardware implementation of CMAC neural network with reduced storage requirement [J].
Ker, JS ;
Kuo, YH ;
Wen, RC ;
Liu, BD .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (06) :1545-1556
[10]   Modelling of the cutting tool stresses in machining of Inconel 718 using artificial neural networks [J].
Kurt, Abdullah .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (06) :9645-9657