Title :
Novel Stability Analysis for Recurrent Neural Networks With Multiple Delays via Line Integral-Type L-K Functional
Author :
Zhenwei Liu ; Huaguang Zhang ; Qingling Zhang
Author_Institution :
Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China
Abstract :
This paper studies the stability problem of a class of recurrent neural networks (RNNs) with multiple delays. By using an augmented matrix-vector transformation for delays and a novel line integral-type Lyapunov-Krasovskii functional, a less conservative delay-dependent global asymptotical stability criterion is first proposed for RNNs with multiple delays. The obtained stability result is easy to check and improve upon the existing ones. Then, two numerical examples are given to verify the effectiveness of the proposed criterion.
Keywords :
Lyapunov methods; delays; matrix algebra; recurrent neural nets; Lyapunov-Krasovskii functional; RNN; line integral type L-K functional; matrix vector transformation; multiple delays; novel stability analysis; recurrent neural networks; Asymptotic stability; Delay; Linear matrix inequalities; Numerical stability; Recurrent neural networks; Stability criteria; Augmented matrix-vector transformation; global asymptotical stability; line integral-type Lyapunov-Krasovskii (L-K) functional; multiple delays; recurrent neural networks (RNNs); Algorithms; Computer Simulation; Mathematical Computing; Neural Networks (Computer); Nonlinear Dynamics; Time Factors;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2010.2054107
