Application of Neural Networks to Inverse Problems in Electromagnetics

Abstract

The paper presents a neural network approach for solving inverse problems in electromagnetics. In general, the measurements of the scattered electromagnetic fields can be related to the properties of the scatterer through integral equations. The energy minimization property of Hopfield neural networks is exploited to solve these integral equations. Results of implementing the method on an application problem involving reconstruction of material properties of multilayered media are presented. © 1994 IEEE