CELLULAR NEURAL NETWORKS WITH MULTIPLE-VALUED OUTPUT AND ITS APPLICATION

Various applications of cellular neural network (CNN) are reported suc h as a feature extraction of the patterns, an extraction of the edges or corners of a figure, noise exclusion, searching in maze and so fort h. In this paper, we propose a cellular neural network whose each cell has more than two output levels. By using the output function which h as several saturated levels, each cell turns to have several output st ates. The multiple-valued CNN enhances its associative memory function so as to express various kinds of aspects. We report an application o f the enhanced associative memory function to a diagnosis of the liver troubles.