Title :
Globally exponential stability of neural networks with variable delays
Author_Institution :
Nat. Traction Power Lab., Southwest Jiaotong Univ., Chengdu, China
fDate :
2/1/2003 12:00:00 AM
Abstract :
In this brief, the conditions ensuring existence, uniqueness, and globally exponential stability of the equilibrium point of neural networks with variable delays are studied. Applying the ideas of the vector Lyapunov function and M-matrix theory, sufficient conditions for global exponential stability of neural networks are obtained.
Keywords :
Lyapunov methods; asymptotic stability; delay-differential systems; delays; matrix algebra; neural nets; stability criteria; M-matrix theory; continuous neuron activation functions; delayed differential equations; equilibrium point; existence; globally exponential stability; neural networks; nonsymmetric interconnection matrices; stability conditions; sufficient conditions; symmetric interconnection matrices; uniqueness; variable delays; vector Lyapunov function; Biological neural networks; Chaos; Chaotic communication; Circuit stability; Delay effects; Frequency response; Neural networks; Neurons; Operational amplifiers; Oscillators;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
DOI :
10.1109/TCSI.2002.808208
