Title :
Discrete-time Zhang neural network and numerical algorithm for time-varying quadratic minimization
Author :
Zhang, Yunong ; Mu, Bingguo ; Zheng, Huicheng
Author_Institution :
Sch. of Inf. Sci. & Technol., Sun Yat-sen Univ., Guangzhou, China
Abstract :
A special class of recurrent neural network (RNN), termed Zhang neural network (ZNN), has been proposed, generalized and investigated for online solution of time-varying problems by following Zhang et al´s design method since 2001. For possible digital hardware realization, discrete-time ZNN models are proposed and investigated in this paper for time-varying quadratic minimization (QM). The proposed discrete-time ZNN models could utilize the time-derivative information of time-varying coefficients. For comparison, a discrete-time gradient neural network (GNN) model is also presented to solve the same time-varying QM problem. Simulative and numerical results demonstrate the efficacy and superiority of the proposed discrete-time ZNN models for time-varying QM, in comparison with the discrete-time GNN model.
Keywords :
discrete time systems; minimisation; numerical analysis; quadratic programming; recurrent neural nets; time-varying systems; discrete-time Zhang neural network; discrete-time gradient neural network model; numerical algorithm; recurrent neural network; time-derivative information; time-varying QM problem; time-varying coefficients; time-varying quadratic minimization; Computational modeling; Hardware; Integrated circuit modeling; Mathematical model; Numerical models; Problem-solving; Vectors;
Conference_Titel :
Cybernetics and Intelligent Systems (CIS), 2011 IEEE 5th International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-61284-199-1
DOI :
10.1109/ICCIS.2011.6070353