Title :
Global Exponential Stability Analysis of Cohen–Grossberg Neural Networks
Author_Institution :
Dept. of Comput. Sci. & Eng., Shanghai Jiao Tong Univ., China
Abstract :
In this paper, we investigate the global exponential stability of the Cohen–Grossberg neural networks with time delays, we derive a general sufficient condition ensuring global stability of the neural networks by constructing a novel Lyapunov functional and carefully estimating its derivative. The main advantage of the proposed condition is the drop of the absolute symbol from the absolute values of the self feedback connection weights, thus improves some existing conditions. As a result, some stability conditions for the Cohen–Grossberg neural network without delays are also derived, which generalize and unify some previous results.
Keywords :
Lyapunov matrix equations; analogue circuits; asymptotic stability; cellular neural nets; circuit stability; delays; difference equations; network analysis; Cohen-Grossberg neural networks; Lyapunov function; M-matrix; global exponential stability; self feedback connection weights; sufficient condition; time delay; Cellular neural networks; Delay effects; Delay estimation; Hopfield neural networks; Neural networks; Neurofeedback; Neurons; Stability analysis; Sufficient conditions; Symmetric matrices; Cohen–Grossberg neural networks; global exponential stability; time delay;
Journal_Title :
Circuits and Systems II: Express Briefs, IEEE Transactions on
DOI :
10.1109/TCSII.2005.850451