MODELING AND SIMULATION OF ZHANG NEURAL NETWORK FOR ONLINE LINEAR TIME-VARYING EQUATIONS SOLVING BASED ON MATLAB SIMULINK
Recently, a general recurrent neural network (RNN) with implicit dynamics has been proposed by Zhang et al for online time-varying algebraic equations solving; namely, Zhang neural network (ZNN). In this type of network systems, neural dynamics are elegantly Introduced by defining a matrix-valued error-monitoring function rather than the usual norm-based scalar-valued error function. This makes the computational error decrease to zero globally and exponentially. This paper investigates the modeling and simulation of ZNN using MATLAB Simulink and presents its convergence and robustness performance. MATLAB Simulink modeling results substantiate that this neural network is efficient for solving online linear time-varying equations.
Recurrent neural network Implicit dynamics time- varying linear equations MATLAB Simulink modeling
YU-NONG ZHANG XIAO-JIAO GUO WEI-MU MA
Department of Electronics and Communication Engineering, Son Yat-Sen University.Guangzhou 510275, Ch School of Software Son Yat-Sen University.Guangzhou 510275, China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
805-810
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）