%0 Journal Article
%T Spatio-Temporal Dynamics in Cellular Neural Networks
%A Liviu GORAS
%J Annals of Dunarea de Jos
%D 2009
%I Universitatea Dunarea de Jos
%X Analog Parallel Architectures like Cellular Neural Networks (CNNĄŻs) have been thoroughly studied not only for their potential in high-speed image processing applications but also for their rich and exciting spatio-temporal dynamics. An interesting behavior such architectures can exhibit is spatio-temporal filtering and pattern formation, aspects that will be discussed in this work for a general structure consisting of linear cells locally and homogeneously connected within a specified neighborhood. The results are generalizations of those regarding Turing pattern formation in CNNĄŻs. Using linear cells (or piecewise linear cells working in the central linear part of their characteristic) allows the use of the decoupling technique ¨C a powerful technique that gives significant insight into the dynamics of the CNN. The roles of the cell structure as well as that of the connection template are discussed and models for the spatial modes dynamics are made as well.
%K analog parallel architectures
%K Cellular Neural Networks
%K spatio-temporal dynamics
%K spatial filters
%U http://www.ann.ugal.ro/eeai/archives/2009/Lucrare-01-Goras.pdf