DocumentCode :
2772992
Title :
Discrete-time Zhang neural network and numerical algorithm for time-varying linear equations solving
Author :
Zhang, Yunong ; Mu, Bingguo ; Zheng, Huicheng
Author_Institution :
Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
fYear :
2011
fDate :
7-10 Aug. 2011
Firstpage :
938
Lastpage :
943
Abstract :
Since 2001, a special class of recurrent neural network (RNN), termed Zhang neural network (ZNN), has been proposed, generalized and exploited for online solution of time-varying problems by following Zhang et al´s design method. In this paper, for possible digital hardware realization, discrete-time ZNN models are proposed and investigated for time-varying linear equations solving. Such discrete-time ZNN models make use of time-derivative information of the time-varying coefficients. For comparison purposes, a discrete-time gradient-based neural network (GNN) model is also presented to solve the same problem. Simulative and numerical results illustrate the efficacy and superiority of these discrete-time ZNN models used for time-varying linear equations solving, as compared to the GNN model.
Keywords :
discrete time systems; gradient methods; recurrent neural nets; time-varying systems; GNN model; discrete-time ZNN model; discrete-time Zhang neural network; discrete-time gradient-based neural network; numerical algorithm; recurrent neural network; time-derivative information; time-varying coefficient; time-varying linear equations solving; time-varying problem; Computational modeling; Equations; Mathematical model; Numerical models; Recurrent neural networks; Steady-state; Vectors; Zhang neural network (ZNN); discrete-time; numerical algorithm; time-varying linear equations;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mechatronics and Automation (ICMA), 2011 International Conference on
Conference_Location :
Beijing
ISSN :
2152-7431
Print_ISBN :
978-1-4244-8113-2
Type :
conf
DOI :
10.1109/ICMA.2011.5985716
Filename :
5985716
Link To Document :
بازگشت