A New Synthesis Procedure for a Class ofCellular Neural Networks withSpace - Invariant Cloning

| This paper presents a new synthesis procedure (design algorithm) for cellular neural networks with space-invariant cloning template with applications to associative memories. In the present synthesis procedure, the design problem is formulated as a set of linear inequalities and the inequalities are solved using the well-known percep-tron training algorithm. When desired memory patterns are given by a set of bipolar vectors, it is guaranteed that a cellular neural network with space-invariant cloning template can be designed using the design algorithm developed herein. An algorithm is also provided to design cellular neu-ral networks with space-invariant cloning template and with symmetric connection matrix to guarantee the global stability of the network. Two speciic examples are included to demonstrate the applicability of the methodology developed herein.