Learning Direct and Inverse Transmission Matrices
Machine Learning
2019-02-05 v2 Machine Learning
Computational Physics
Optics
Computation
Abstract
Linear problems appear in a variety of disciplines and their application for the transmission matrix recovery is one of the most stimulating challenges in biomedical imaging. Its knowledge turns any random media into an optical tool that can focus or transmit an image through disorder. Here, converting an input-output problem into a statistical mechanical formulation, we investigate how inference protocols can learn the transmission couplings by pseudolikelihood maximization. Bridging linear regression and thermodynamics let us propose an innovative framework to pursue the solution of the scattering-riddle.
Cite
@article{arxiv.1901.04816,
title = {Learning Direct and Inverse Transmission Matrices},
author = {Daniele Ancora and Luca Leuzzi},
journal= {arXiv preprint arXiv:1901.04816},
year = {2019}
}