Pattern memory and acquisition based on stability of cellular neural networks

In this paper, some sufficient conditions are obtained to guarantee that the n-dimensional cellular neural networks can have even (/spl les/2/sup n/) memory patterns. And we have obtained the estimates of attracting domain of such stable memory patterns. Those conditions directly derived from the parameters of the neural networks, are very easy to verified. A new design algorithm for cellular neural networks is developed based on stability theory (not base on the well-known perceptron training algorithm), and the convergence of the design algorithm is guaranteed by some stability theorems. The results presented in this paper are new. Finally, the validity and performance of the results are illustrated by simulation results.