Title :
Absolute periodicity and absolute stability of delayed neural networks
Author :
Yi, Zhang ; Heng, Pheng Ann ; Vadakkepat, Prahlad
Author_Institution :
Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Shatin, China
fDate :
2/1/2002 12:00:00 AM
Abstract :
Proposes to study the absolute periodicity of delayed neural networks. A neural network is said to be absolutely periodic, if for every activation function in some suitable functional set and every input periodic vector function, a unique periodic solution of the network exists and all other solutions of the network converge exponentially to it. Absolute stability of delayed neural networks is also studied in this paper. Simple and checkable conditions for guaranteeing absolute periodicity and absolute stability are derived. Simulations for absolute periodicity are given
Keywords :
absolute stability; delays; neural nets; transfer functions; absolute periodicity; absolute stability; activation function; checkable conditions; delayed neural networks; functional set; input periodic vector function; Automatic control; Control systems; Delay lines; Delay systems; Linear matrix inequalities; Neural networks; Robust stability; Sun; Time varying systems; Uncertain systems;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
