Title :
Generalized cellular neural networks represented in the NLq framework
Author :
Suykens, Johan ; Vandewalle, Joos
Author_Institution :
Dept. of Electr. Eng., Katholieke Univ., Leuven, Heverlee, Belgium
fDate :
30 Apr-3 May 1995
Abstract :
The aim of this paper is to show that discrete time Generalized Cellular Neural Networks, with feedforward, feedback or cascade interconnections between CNNs can be represented as NLqs. NL qs are nonlinear systems in state space form with the typical feature of having a number of q layers with alternating linear and nonlinear operators that satisfy a sector condition. It can be shown that many systems and problems arising in neural networks, systems and control are special cases of NLqs. Sufficient conditions for global asymptotic stability and dissipativity with finite L2-gain are available. For q=1 the criteria are closely related to known results in H∞ and μ control theory
Keywords :
asymptotic stability; cellular neural nets; feedforward neural nets; recurrent neural nets; state-space methods; cascade interconnections; dissipativity; feedback interconnections; feedforward interconnections; generalized cellular neural networks; global asymptotic stability; nonlinear systems; sector condition; state space form; Asymptotic stability; Cellular neural networks; Control systems; Electronic mail; Intelligent networks; Neural networks; Nonlinear equations; Nonlinear systems; Stability criteria; State-space methods;
Conference_Titel :
Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2570-2
DOI :
10.1109/ISCAS.1995.521596
