Geodesic
Performance Analyses of Recurrent Neural Network Models Exploited for Online Time-Varying Nonlinear Optimization
Computer Science and Information Systems, Tome 13 (2016) no. 2 Cet article a éte moissonné depuis la source Computer Science and Information Systems website

Voir la notice de l'article

In this paper, a special recurrent neural network (RNN), i.e., the Zhang neural network (ZNN), is presented and investigated for online time-varying nonlinear optimization (OTVNO). Compared with the research work done previously by others, this paper analyzes continuous-time and discrete-time ZNN models theoretically via rigorous proof. Theoretical results show that the residual errors of the continuous-time ZNN model possesses a global exponential convergence property and that the maximal steady-state residual errors of any method designed intrinsically for solving the static optimization problem and employed for the online solution of OTVNO is O(τ ), where τ denotes the sampling gap. In the presence of noises, the residual errors of the continuous-time ZNN model can be arbitrarily small for constant noises and random noises. Moreover, an optimal sampling gap formula is proposed for discrete-time ZNN model in the noisy environments. Finally, computer-simulation results further substantiate the performance analyses of ZNN models exploited for online time-varying nonlinear optimization.
Keywords: performance analysis, Zhang neural network (ZNN), online time-varying nonlinear optimization (OTVNO), Newton conjugate gradient model 
@article{CSIS_2016_13_2_a22,
     author = {Mei Liu and Bolin Liao and Lei Ding and Lin Xiao},
     title = {Performance {Analyses} of {Recurrent} {Neural} {Network} {Models} {Exploited} for {Online} {Time-Varying} {Nonlinear} {Optimization}},
     journal = {Computer Science and Information Systems},
     year = {2016},
     volume = {13},
     number = {2},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2016_13_2_a22/}
}
TY  - JOUR
AU  - Mei Liu
AU  - Bolin Liao
AU  - Lei Ding
AU  - Lin Xiao
TI  - Performance Analyses of Recurrent Neural Network Models Exploited for Online Time-Varying Nonlinear Optimization
JO  - Computer Science and Information Systems
PY  - 2016
VL  - 13
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/CSIS_2016_13_2_a22/
ID  - CSIS_2016_13_2_a22
ER  - 
%0 Journal Article
%A Mei Liu
%A Bolin Liao
%A Lei Ding
%A Lin Xiao
%T Performance Analyses of Recurrent Neural Network Models Exploited for Online Time-Varying Nonlinear Optimization
%J Computer Science and Information Systems
%D 2016
%V 13
%N 2
%U http://geodesic.mathdoc.fr/item/CSIS_2016_13_2_a22/
%F CSIS_2016_13_2_a22
Mei Liu; Bolin Liao; Lei Ding; Lin Xiao. Performance Analyses of Recurrent Neural Network Models Exploited for Online Time-Varying Nonlinear Optimization. Computer Science and Information Systems, Tome 13 (2016) no. 2. http://geodesic.mathdoc.fr/item/CSIS_2016_13_2_a22/