Title
An estimation of the domain of attraction for recurrent neural networks with time-varying delays
Abstract
Based on Lyapunov-Krasovskii functional or Lyapunov-Razumikhin functional method and invariant set principle, we presented a new method to estimate the domain of attraction for general recurrent neural networks with time-varying delays. Convex optimization method is proposed to enlarge and estimate the domain of attraction. Local exponential stability conditions are derived, which can be expressed as linear matrix inequalities (LMIs) in terms of all the varying parameters and hence can be easily checked in both analysis and design.
Year
DOI
Venue
2008
10.1016/j.neucom.2007.04.013
Neurocomputing
Keywords
Field
DocType
local exponential stability condition,general recurrent neural network,linear matrix inequality,invariant set principle,convex optimization method,new method,varying parameter,time-varying delay,lyapunov-razumikhin functional method,recurrent neural network,neural network,convex optimization,recurrent neural networks,exponential stability
Mathematical optimization,Matrix (mathematics),Recurrent neural network,Exponential stability,Invariant (mathematics),Attraction,Convex optimization,Linear matrix inequality,Mathematics
Journal
Volume
Issue
ISSN
71
7-9
Neurocomputing
Citations 
PageRank 
References 
5
0.49
16
Authors
4
Name
Order
Citations
PageRank
Jun Xu1313.33
Yong-Yan Cao21123106.27
Daoying Pi3509.21
Youxian Sun42707196.15