A new synthesis procedure for a class of cellular neural networks with space-invariant cloning template

This paper presents a new synthesis procedure (design algorithm) for cellular neural networks (CNN's) with a 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 perceptron training algorithm. Then desired memory patterns are given by a set of bipolar vectors, it is guaranteed that a cellular neural network with a space-invariant cloning template can be designed using the design algorithm developed herein. An algorithm is also provided to design CNN's with space-invariant cloning templates and with symmetric connection matrices to guarantee the global stability of the network. Two specific examples are included to demonstrate the applicability of the methodology developed herein.

[1]  A.N. Michel,et al.  Associative memories via artificial neural networks , 1990, IEEE Control Systems Magazine.

[2]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[3]  J. Mycielski.  Review: Marvin Minsky and Seymour Papert, Perceptrons, An Introduction to Computational Geometry , 1972 .

[4]  Josef A. Nossek,et al.  Design of robust cellular neural networks , 1993 .

[5]  Derong Liu,et al.  Robustness analysis and design of a class of neural networks with sparse interconnecting structure , 1996, Neurocomputing.

[6]  A. Michel,et al.  Dynamical Systems with Saturation Nonlinearities: Analysis and Design , 1994 .

[7]  Derong Liu,et al.  Cloning template design of cellular neural networks for associative memories , 1997 .

[8]  Derong Liu,et al.  Sparsely interconnected neural networks for associative memories with applications to cellular neural networks , 1994 .

[9]  Mancia Anguita,et al.  Analog CMOS implementation of a discrete time CNN with programmable cloning templates , 1993 .

[10]  R. Perfetti,et al.  Associative memory design using space-varying cellular neural networks , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[11]  B. Ling,et al.  A cellular network formed of Hopfield networks , 1992, [1992] Proceedings of the 35th Midwest Symposium on Circuits and Systems.

[12]  M. Brucoli,et al.  Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities , 1995 .

[13]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[14]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[15]  Derong Liu,et al.  A new synthesis approach for feedback neural networks based on the perceptron training algorithm , 1997, IEEE Trans. Neural Networks.