Title :
Some new results on system identification with dynamic neural networks
Author :
Yu, Wen ; Li, XiaoOu
Author_Institution :
Dept. de Control Autom., CINVESTAV-IPN, Mexico City, Mexico
fDate :
3/1/2001 12:00:00 AM
Abstract :
Nonlinear system online identification via dynamic neural networks is studied in this paper. The main contribution of the paper is that the passivity approach is applied to access several new stable properties of neuro identification. The conditions for passivity, stability, asymptotic stability, and input-to-state stability are established in certain senses. We conclude that the gradient descent algorithm for weight adjustment is stable in an L∞ sense and robust to any bounded uncertainties
Keywords :
gradient methods; identification; neural nets; nonlinear systems; online operation; stability; L∞ stability; asymptotic stability conditions; bounded uncertainty robustness; dynamic neural networks; gradient descent algorithm; input-to-state stability conditions; neuro identification; nonlinear system online identification; passivity approach; passivity conditions; stability criteria; stable properties; weight adjustment; Asymptotic stability; Circuit stability; Multilayer perceptrons; Neural networks; Nonlinear control systems; Nonlinear systems; Robustness; Stability analysis; System identification; Uncertainty;
Journal_Title :
Neural Networks, IEEE Transactions on
