Paper Info
Title
Performance analyses of recurrent neural network models exploited for online time-varying nonlinear optimization.
Abstract
In this paper, a special recurrent neural network (RNN), i.e., the Zhang neural network (ZNN), is presented and investigated for online time-varying non-linear 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(T), where T 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.
Year
DOI
Venue
2016
10.2298/CSIS160215023L
COMPUTER SCIENCE AND INFORMATION SYSTEMS
Keywords
Field
DocType
performance analysis,Zhang neural network (ZNN),online time-varying nonlinear optimization (OTVNO),Newton conjugate gradient model
Residual,Mathematical optimization,Zhang neural network,Static optimization,Computer science,Nonlinear programming,Recurrent neural network,Sampling (statistics),Artificial intelligence,Exponential convergence,Machine learning
Journal
Volume
Issue
ISSN
13
2
1820-0214
Citations 
PageRank 
References 
2
0.36
0
Authors
4
Name
Order
Citations
PageRank
Mei Liu120.70
Bolin Liao228118.70
Lei Ding314226.77
Lin Xiao456242.84