Title :
Continuous time NLq theory: absolute stability criteria
Author :
Suykens, J.A.K. ; Vandewalle, J.
Author_Institution :
ESAT, Katholieke Univ., Leuven, Heverlee, Belgium
Abstract :
We present absolute stability (global asymptotic) criteria for continuous time multilayer recurrent neural networks with two hidden layers. Such forms arise when considering recurrent neural models and neural controllers for a given plant, both parametrized by multilayer perceptrons with one-hidden layer. The one-hidden layer case corresponds to systems in Lur´e form. These results are related to the NLq theory which is a stability theory for q-layered discrete time multilayer recurrent neural networks with conditions for global asymptotic stability and input-output stability with finite L2-gain. The criteria can be used to constrain dynamic backpropagation in order to impose closed-loop stability for neural control schemes
Keywords :
absolute stability; asymptotic stability; backpropagation; closed loop systems; feedforward neural nets; multilayer perceptrons; neurocontrollers; recurrent neural nets; Lure form; NLq theory; absolute stability; asymptotic stability; backpropagation; closed-loop systems; multilayer neural networks; multilayer perceptrons; neurocontrollers; recurrent neural networks; Asymptotic stability; Backpropagation; Constraint theory; Linear feedback control systems; Linear matrix inequalities; Multi-layer neural network; Nonhomogeneous media; Nonlinear dynamical systems; Recurrent neural networks; Stability criteria;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832587
