Learning Direct and Inverse Transmission Matrices
This addresses the challenge of focusing or transmitting images through disorder in biomedical imaging, but appears incremental as it builds on existing linear regression and thermodynamic concepts.
The paper tackles the problem of recovering transmission matrices in biomedical imaging by converting it into a statistical mechanical formulation, achieving a novel framework for solving scattering issues through pseudolikelihood maximization.
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.