As. Sherstinsky et Rw. Picard, ON STABILITY AND EQUILIBRIA OF THE M-LATTICE, IEEE transactions on circuits and systems. 1, Fundamental theory andapplications, 45(4), 1998, pp. 408-415
Both the analog Hopfield network [1] and the cellular neural network [
2], [3] are special cases of the M-lattice system, recently introduced
to the signal processing community [4]-[6], We prove that a subclass
of the M-lattice is totally stable. This result also applies to the or
iginal cellular neural network [2] as a rigorous proof of its total st
ability. By analyzing the stability of fixed points, we derive the con
ditions for driving the equilibrium outputs of another subclass of the
M-lattice to binary values, For the cellular neural network, this ana
lysis is a precise formulation of an earlier argument based on circuit
diagrams [2], And for certain special cases of the analog Hopfield ne
twork, this analysis explains why the output variables converge to bin
ary values even with nonzero neuron auto-connections. This behavior, o
bserved in computer simulation by researchers for quite some time, is
explained for the first time here.