Title :
A geometric approach to properties of the discrete-time cellular neural network
Author :
Magnussen, Holger ; Nossek, Josef A.
Author_Institution :
Network Theory & Circuit Design, Tech. Univ. Munchen, Germany
fDate :
10/1/1994 12:00:00 AM
Abstract :
Using the available theory on linear threshold logic, the Discrete-Time Cellular Neural Network (DTCNN) is studied from a geometrical point of view, Different modes of operation are specified. A bound on the number of possible mappings is given for the case of binary inputs. The mapping process in a cell of the network is interpreted in the input space and the parameter space. Worst-case and average-case accuracy conditions are given, and a sufficient worst-case bound on the number of bits required to store the network parameters for the case of binary input signals is derived. Methods for optimizing the robustness of DTCNN parameters for certain regions of the parameter space are discussed
Keywords :
cellular neural nets; discrete time systems; network parameters; threshold logic; accuracy conditions; discrete-time cellular neural network; linear threshold logic; mapping process; network parameters storage; operation modes; Cellular neural networks; Character generation; Equations; Glass; Helium; Integrated circuit interconnections; Logic; Optimization methods; Robustness; Temperature;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
