Training with noise as a method to increase noise resilience of neural network solution of inverse problems

Abstract

Inverse problems constitute a special class of problems, which consist in reconstruction of parameters of an object by the data of indirect measurements, which are affected by these parameters. Many inverse problems are ill-posed (incorrect), i.e., characterized by nonuniqueness and/or instability of the solution. Improvement in the stability of the solution of inverse problems is a very topical problem; one of the ways to solve it is the use of artificial neural networks. In the present study, at the example of a model 5-parameter inverse problem it is demonstrated that adding noise to the training set when training neural networks allows one to improve resilience of the neural network solution to noise in input data, with various distribution and intensity of noise.