Sensitivity driven artificial neural network correction models for RF/microwave devices

Abstract

In this article, we propose a sensitivity based correction model that improves the accuracy of the neural model keeping the structure of artificial neural network (ANN) simple. The proposed approach is applied to the modeling of RF transistors, spiral inductors, and microstrip antennas. Results are compared with conventional ANN and a recent technique referred to as correction model that is assisted by the regula-falsi method. © 2011 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2012.