A method for designing CNN templates

Cellular neural networks (CNN) are very useful for image processing tasks [1], [2]. One problem with CNN networks is the lack of a programming method to realize a processing task. The cloning templates entirely specifies the programming of a CNN net. There are a lot of cloning templates for several tasks [3]-[4], got by mathematical analysis or heuristically [4]-[9]. However for some specific tasks is very difficult to find the correct templates. In this paper a procedure for finding cloning templates for image processing tasks is described, using a gradient method. A set of CNN templates obtained using the proposed procedure is shown.