Corso Duca degli Abruzzi, 24Abstmct-Cellular neural networks (CNNs) are described by large systems of locally coupled nonlinear differential equations. In most applications the connections are specified through space-invariant templates. As far as the dynamic behavior is concerned, CNNs can b e divided in two main classes: stable CNNs, with the property that each trajectory (with the exception of a set of measure zero) converges towards a n equilibrium point; unstable CNNs, that exhibit at least one attractor, that is not a stable equilibrium point. Due t o their complex dynamics, only a few methods for template design have been so far proposed. We propose a rigorous design algorithm for stable CNNs and we identify the class of templates to which such an algorithm can be applied.