Multimode optical fiber transmission with a deep learning network

Abstract

Multimode fibers (MMFs) are an example of a highly scattering medium, which scramble the coherent light propagating within them to produce seemingly random patterns. Thus, for applications such as imaging and image projection through an MMF, careful measurements of the relationship between the inputs and outputs of the fiber are required. We show, as a proof of concept, that a deep neural network can learn the input-output relationship in a 0.75 m long MMF. Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the nonlinear relationships between the amplitude of the speckle pattern (phase information lost) obtained at the output of the fiber and the phase or the amplitude at the input of the fiber. Effectively, the network performs a nonlinear inversion task. We obtained image fidelities (correlations) as high as ~98% for reconstruction and ~94% for image projection in the MMF compared with the image recovered using the full knowledge of the system transmission characterized with the complex measured matrix. We further show that the network can be trained for transfer learning, i.e., it can transmit images through the MMF, which belongs to another class not used for training/testing.

Physical Layer Security in Multimode Fiber Optical Networks

“…The T M approach proved to be extremely helpful to overcome the challenge to use the MMF either as an imaging [22,23,24,25,26] or data transmitting tool [34,30] for compensating the fiber's light scrambling property. Besides experimental techniques to determine the T M , approaches to identify the T M via deep learning [35,36] or convex optimization algorithms [37] have already been shown. The T M describes the linear and complex relationship between input and output of the MMF exactly.…”

Controlling spatiotemporal nonlinearities in multimode fibers with deep neural networks

“…Recently, machine learning tools have been proposed to simplify the calibration and improve the robustness of the system in the absence of optical nonlinearities 18 . Deep neural networks (DNNs) proved useful for classification/ reconstruction of the information sent to km-long MMFs solely from the intensity measurement at the output of the fibers 19,20 . For the nonlinear propagation regime, only adaptive algorithms have been brought forth and been shown to be successful in harnessing the entangled spatiotemporal nonlinearities such as Kerr beam self-cleaning of loworder modes 21 and optimization of the intensity of targeted spectral peaks generated by Raman scattering or four-wave In this article, we report the results of our studies on the effect of initial excitation condition of the GRIN MMFs to nonlinear spatiotemporal propagation by employing machine learning approaches.…”

Deep learning enabled real time speckle recognition and hyperspectral imaging using a multimode fiber array

“…Computational methods using neural networks that are trainable for specific problems have recently been shown to be highly efficient and fast [35,36,37]. Recently, this approach has been used in various applications utilizing speckle patterns such as image reconstruction, object classification and recognition [38,39,40,41,42,43,44].…”