Actor neural networks for the robust control of partially measured nonlinear systems showcased for image propagation through diffuse media

Babak Rahmani, Damien Loterie, Eirini Kakkava, Navid Borhani, Ugur Tegin, Demetri Psaltis, Christophe Moser

Abstract: Machine learning has become popular in solving complex optical problems such as recovering the input phase and amplitude for a specific pattern or image measured through a scattering medium. In a more challenging application, Rahmani et al. consider the problem of also producing desired outputs for such a nonlinear system when only some intensity-only measurements of example outputs are available. They develop a neural network approach that can ensure the transmission of images through a highly nonlinear system—a multimode fibre—with a 90% fidelity.