Dynamic Analysis of Coupled Binary Stripe CNNs
Qun Zhang, Lequan Min · 2011
The robust designs for cellular neural network (CNN) templates is one of the important issues for the practical applications of CNNs. This paper establishes 6 theorems for describe the performance of coupled binary stripe (CBS) CNNs. The theorems interpret why the CBS CNNs can generate always striped patterns from any random binary initial patterns. Three examples are presented to illustrate the effectiveness of the methodology.