Title :
On stability of recurrent neural networks-an approach from volterra integro-differential equations
Author :
Liu, Pingzhou ; Han, Qing-Long
Abstract :
The uniform asymptotic stability of recurrent neural networks (RNNs) with distributed delay is analyzed by comparing RNNs to linear Volterra integro-differential systems under Lipschitz continuity of activation functions. The stability criteria obtained have unified and extended many existing results on RNNs.
Keywords :
Volterra equations; integro-differential equations; recurrent neural nets; stability; stability criteria; Lipschitz continuity; Volterra integro-differential equations; asymptotic stability; distributed delay; recurrent neural networks stability; stability criteria; Asymptotic stability; Electronic mail; Informatics; Integrodifferential equations; Kernel; Neural networks; Recurrent neural networks; Stability criteria; Delay; Volterra integro-differential systems; recurrent neural networks (RNNs); stability;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.860859
