Title :
Global asymptotic stability of delayed Cohen-Grossberg neural networks
Author_Institution :
Dept. of Math., Wilfrid Laurier Univ., Waterloo, Ont., Canada
Abstract :
In this paper, we study the Cohen-Grossberg neural networks with discrete and distributed delays. For a general class of internal decay functions, without assuming the boundedness, differentiability, and monotonicity of the activation functions, we establish some sufficient conditions for the existence of a unique equilibrium and its global asymptotic stability. Theory of M-matrices and Lyapunov functional technique are employed. The criteria are independent of delays and hence delays are harmless in our case. Our results improve and generalize some existing ones.
Keywords :
asymptotic stability; delays; matrix algebra; neural nets; Lyapunov functional technique; M-matrices theory; activation functions; delayed Cohen-Grossberg neural networks; discrete delays; distributed delays; global asymptotic stability; internal decay functions; Artificial neural networks; Asymptotic stability; Delay effects; Design optimization; Differential equations; Hopfield neural networks; Neural networks; Pattern recognition; Sufficient conditions; Symmetric matrices; Cohen–Grossberg neural network; discrete delay; distributed delay; equilibrium; global (asymptotic) stability;
Journal_Title :
Circuits and Systems I: Regular Papers, IEEE Transactions on
DOI :
10.1109/TCSI.2005.856047
