K. Nakai et A. Ushida, DESIGN TECHNIQUE OF CELLULAR NEURAL-NETWORK, Electronics and communications in Japan. Part 3, Fundamental electronic science, 78(3), 1995, pp. 97-107
The cellular neural network (CNN) is composed of a planar placement of
cells which consists of a (piecewise-linear) nonlinear element and co
ntrolled current sources. It features a simple structure which is clos
e to that of the retina and is expected to be utilized in pattern reco
gnition and image processing. In CNN, each cell is connected to the ne
ighborhood cells by the same pattern, and by adjusting the connection
pattern, CNN with various functions can be designed. The connection pa
ttern is called the cloning template. It is very important in the deve
lopment of new CNN to establish the design method for the cloning temp
late. In this paper, the operational characteristics are assumed so th
at the output for the normative input satisfies the specified conditio
ns. The constraint is derived from the specification and the template
is designed so that the corresponding cost function is minimized. The
simplex method is used as the optimization technique, which features a
simple algorithm. As application examples, noise-remover CNN as well
as the maze-tracing CNN are designed and satisfactory results are obta
ined. The design method is reported in this paper.