Neuromodeling of microwave circuits exploiting space mapping technology
Fecha
1999-06Autor
Bandler, John W.
Ismael, Mohamed H.
Rayas-Sánchez, José E.
Zhang, Qi J.
Metadatos
Mostrar el registro completo del ítemDescripción
For the first time, we present neuromodeling of microwave circuits based on Space Mapping (SM) technology. SM based neuromodels decrease the cost of training, improve generalization ability and reduce the complexity of the ANN topology w.r.t. classical neuromodeling. Three novel techniques are proposed to generate SM based neuromodels: Space-Mapped Neuromodeling (SMN), Frequency-Dependent Space-Mapped Neuromodeling (FDSMN), and Frequency Space-Mapped Neuromodeling (FSMN). Huber optimization is proposed to train the neuro-space-mapping (NSM). The techniques are illustrated by a microstrip right angle bend and a microstrip line with high dielectric constant.Consejo Nacional de Ciencia y Tecnología