In this work a new approach based on artificial neural networks (ANNs) was successfully introduced to determine the characteristic parameters of conventional coplanar waveguides (CPWs) and CPW sandwiched between two dielectric substrates. Only one neural model was used to calculate the characteristic parameters of conventional CPWs and sandwiched CPWs. This neural model was trained with extended delta-bar-delta (EDBD). The characteristic parameters obtained from neural model are in very good agreement with theoretical and experimental results available in the literature. The neural model presented in this work is not time consuming and easily included in CAD systems.