Reachable Set Analysis for Dynamic Neural Networks with Polytopic Uncertainties

In this paper,the reachable set estimation problem is studied for a class of dynamic neural networks subject to polytopic uncertainties.The problem addressed here is to find a set as small as possible to bound the states starting from the origin by inputs with peak values.The maximal Lyapunov functi...

Full description

Saved in:
Bibliographic Details
Published in:Communications in theoretical physics 2012-05, Vol.57 (5), p.904-908
Main Author: 左志强 陈银萍 王一晶
Format: Article
Language:English
Subjects:
Dynamic tests
Dynamics
Estimates
Lyapunov functions
Lyapunov泛函
Neural networks
Origins
Theoretical physics
Uncertainty
不确定性
估计问题
共同Lyapunov函数
动态神经网络
可达集
多面体
神经网络分析
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper,the reachable set estimation problem is studied for a class of dynamic neural networks subject to polytopic uncertainties.The problem addressed here is to find a set as small as possible to bound the states starting from the origin by inputs with peak values.The maximal Lyapunov functional is proposed to derive a sufficient condition for the existence of a non-ellipsoidal bound to estimate the states of neural networks.It is theoretically shown that this method is superior to the traditional one based on the common Lyapunov function.Finally,two examples illustrate the advantages of our proposed result.
ISSN:0253-6102
DOI:10.1088/0253-6102/57/5/23