Title :
Stability analysis of neural-network interconnected systems
Author :
Hwang, Jiing-Dong ; Hsiao, Feng-Hsiag
Author_Institution :
Dept. of Electron. Eng., Jin-Wen Inst. of Technol., Taipei, Taiwan
fDate :
1/1/2003 12:00:00 AM
Abstract :
This paper is concerned with the stability problem of a neural-network (NN) interconnected system which consists of a set of NN models. First, a linear difference inclusion (LDI) state-space representation is established for the dynamics of each NN model. Subsequently, based on the LDI state-space representation, a stability criterion in terms of Lyapunov´s direct method is derived to guarantee the asymptotic stability of NN interconnected systems. Finally, a numerical example with simulations is given to demonstrate the results.
Keywords :
asymptotic stability; neural nets; stability criteria; state-space methods; Lyapunov direct method; linear difference inclusion; neural-network interconnected systems; stability analysis; stability criterion; state-space representation; Asymptotic stability; Biological neural networks; Control systems; Interconnected systems; Neural networks; Neurons; Numerical simulation; Stability analysis; Stability criteria; Transfer functions;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2002.806643
