Multilayer Perceptron Neural model for Conductor- Backed Edge Coupled coplanar waveguides

In microwave and millimeter wave integrated circuits, coplanar waveguides (CPWs) have been used as an alternative to microstrip lines. This paper presents a new approach based on Multilayer Perceptron Neural Networks (MLPNNs) to calculate the characteristic parameters of Conductor- Backed Edge Coupled CPWs(CB-ECCPWs). Neural models were trained with five different algorithms to obtain better performance and faster convergence with a simpler structure. The best results were obtained from the models trained with Levenberg-Marqurat(LM) and Bayesian Regularization(BR) algorithms. The results obtained from the neural models are in very good agreement with the theoretical results available in the literature.