Capacity of cellular neural networks as associative memories

In the paper a cellular neural network (CNN) architecture as an associative memory is considered. The boundary for the maximum number of memory vectors is obtained. The result suggests that the maximum number of memory vectors arbitrarily chosen from a set of linearly independent vectors is not related to the size of CNN but depends only on radius of the neighborhood.

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

[2]  M. Hirsch.  CONVERGENCE IN NEURAL NETS. , 1987 .

[3]  A.N. Michel,et al.  Analysis and synthesis of a class of discrete-time neural networks described on hypercubes , 1991, IEEE Trans. Neural Networks.

[4]  Ömer Morgül,et al.  On the design of dynamic associative neural memories , 1994, IEEE Trans. Neural Networks.

[5]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[6]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Fathi M. A. Salam,et al.  On the analysis of dynamic feedback neural nets , 1991 .