ASSOCIATIVE MEMORIES IN CELLULAR NEURAL NETWORKS USING A SINGULAR-VALUE DECOMPOSITION

Using various templates, many applications of cellular neural network (CNN), such as a feature extraction, an edge detection and a pattern c lassification have been considered. In a Hopfield network, an image to be stored corresponds to the minimum value of the energy of the netwo rk. However, in CNN, an image corresponds to the equilibrium state of a differential equation. A synthesis procedure for designing a CNN tha t will store a set of desired vectors as memory points using a singula r value matrix decomposition is considered. Also analyzed here is the indeterminate phenomenon of the equilibrium states of some cells that arise in the case in which more than two similar patterns are stored f or Chinese characters.