Applied Mathematics and Mechanics (English Edition) ›› 2005, Vol. 26 ›› Issue (3): 372-380 .

• Articles • Previous Articles     Next Articles

GLOBAL ASYMPTOTIC STABILITY CONDITIONS OF DELAYED NEURAL NETWORKS

ZHOU Dong-ming, CAO Jin-de, ZHANG Li-ming   

    1. Department of Electronic Engineering, Fudan University, Shanghai 200433, P.R.China;
    2. Department of Applied Mathematics, Southeast University, Nanjing 210096, P.R.China;
    3. Department of Electronic Engineering, Yunnan University, Kunming 650091, P.R.China
  • Received:2003-04-28 Revised:2004-09-15 Online:2005-03-18 Published:2005-03-18
  • Contact: ZHOU Dong-ming

Abstract: Utilizing the Liapunov functional method and combining the inequality of matrices technique to analyze the existence of a unique equilibrium point and the global asymptotic stability for delayed cellular neural networks (DCNNs), a new sufficient criterion ensuring the global stability of DCNNs is obtained. Our criteria provide some parameters to appropriately compensate for the tradeoff between the matrix definite condition on feedback matrix and delayed feedback matrix. The criteria can easily be used to design and verify globally stable networks. Furthermore,the condition presented here is independent of the delay parameter and is less restrictive than that given in the references.

Key words: cellular neural network, global stability, inequality of matrix, delay

2010 MSC Number: 

APS Journals | CSTAM Journals | AMS Journals | EMS Journals | ASME Journals