Title :
Unifying results in CNN theory using delta operator
Author :
Hänggi, Martin ; Reddy, H. ; Moschytz, G.
fDate :
May 30 1999-June 2 1999
Abstract :
By means of the delta operator, a new type of CNN, the (/spl delta/,c)-CNN, is introduced. It is a superclass of continuous-time (CT) and discrete-time (DT) CNNs with any saturation-, high-gain-, or hardlimiting sign-nonlinearity. It is shown that the (/spl delta/,c)-CNN allows continuous transition between different types of nonlinearities and between CT- and DT-CNNs, providing a unifying framework for CNN theory. In particular, the problem of optimally robust template design can be dealt with in a unified manner.
Keywords :
cellular neural nets; continuous time systems; discrete time systems; (/spl delta/,c)-CNN; CNN theory; continuous-time CNN; delta operator; discrete-time CNN; hardlimiting sign-nonlinearity; high-gain-nonlinearity; optimally robust template design; saturation-nonlinearity; Boundary conditions; Cellular neural networks; Convolution; Information processing; Inspection; Laboratories; Nonlinear equations; Robustness; Signal processing;
Conference_Titel :
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-5471-0
DOI :
10.1109/ISCAS.1999.777630