Machine learning-driven complex models for wavefront shaping through multimode fibers

Abstract

We investigate a method to retrieve full-complex models (Transmission Matrix and Neural Network) of a highly multimode fiber (140 LP modes/polarization) using a straightforward machine learning approach, without the need of a reference beam. The models are first validated by the high fidelity between the predicted and the experimental images in the near field and far field output planes (Pearson correlation coefficient between 97.5% and 99.1% with our trained Transmission Matrix or Neural Network). Their accuracy was further confirmed by successful 3D beam shaping, a task achievable only with a true full complex model. As a prospect, we also demonstrate the ability of our neural network architecture to model nonlinear Kerr propagation in gradient index multimode fiber and predict the output beam shape.

References in corpus (9)

• Space Division Multiplexing in Optical Fibres
• Reference-less measurement of the transmission matrix of a highly scattering material using a DMD and phase retrieval techniques
• Digital confocal microscopy through a multimode fiber
• Controlling light propagation in multimode fibers for imaging, spectroscopy and beyond
• Image transmission through a flexible multimode fiber by deep learning
• Learning and avoiding disorder in multimode fibers
• Controlling spatiotemporal nonlinearities in multimode fibers with deep neural networks
• Wavefront shaping for optimized many-mode Kerr beam self-cleaning in graded-index multimode fiber
• Securing Data in Multimode Fibers by Exploiting Mode-Dependent Light Propagation Effects