Deep neural network based method for electromagnetic source image reconstruction

Abstract

The present disclosure concerns a computer implemented system and method of reconstructing a digital image 50 of an electromagnetic source 10 using a neural network 20, the method including the steps of: receiving an electromagnetic signal 11 acquired by an electromagnetic sensor 12 sensing said electromagnetic source 10, providing the electromagnetic signal 11 as input into a neural network 20 parametrized by a set of parameters θ for determining an estimated electromagnetic source vector 21 associated to the electromagnetic signal, determining a loss function 30, minimizing the loss function 30 by feed-forwarding the neural network 20 until a stop criterion is met to obtain an optimal electromagnetic source vector 40, and reconstructing a digital image 50 of the electromagnetic source 10 based on the optimal electromagnetic source vector 40, wherein determining the loss function 30 includes computing an estimated electromagnetic signal 31 based on the estimated electromagnetic source vector 21.

Dependencies are inferred from the claim text.