B-spline Neural Networks (BSNNs) belong to the class of networks termed grid or lattice-based associative memories networks (AMN). The grid is a key feature since it allows these networks to exhibit relevant properties which make them efficient in solving problems namely, functional approximation, non-linear system identification, and on-line control. The main problem associated with BSNNs is that the model complexity grows exponentially with the number of input variables. To tackle this drawback, different authors developed heuristics for functional decomposition, such as the ASMOD algorithm or evolutionary approaches . In this paper, we present a complementary approach, by allowing the properties of B-spline models to be achieved by non-full grids. This approach can be applied either to a single model or to an ASMOD decomposition. Simulation results show that comparable results, in terms of approximations can be obtained with less complex models.