Circuit CAD and modeling through space mapping
Description
We review the Space Mapping (SM) approach to circuit design and discuss modeling of microwave circuits using Artificial Neural Networks (ANN). We show that SM and ANN methodologies can be combined into a powerful design framework. SM based neuromodels decrease the cost of training, improve generalization ability and reduce the complexity of the ANN topology with respect to the classical neuromodeling approach. We present and illustrate a variety of possible SM based neuromodels, including SMN, FDSMN, FSMN, FMN and FPSM. We contrast SM based neuromodeling with the classical neuromodeling approach as well as with other state-of-the-art neuromodeling techniques. The SM based neuromodeling techniques are illustrated by a microstrip line, a microstrip right angle bend and an HTS filter.Consejo Nacional de Ciencia y Tecnología