Multimode Optical Fiber Transmission With A Deep Learning Network

Science applications 7 1 december 2018 with 213 reads how we measure reads.

Multimode optical fiber transmission with a deep learning network.

Multi mode fiber is a type of optical fiber designed to carry multiple light rays or modes simultaneously each at a marginally different reflection angle inside the optical fiber core. The researchers used the experimentally measured transmission matrix of the multimode fiber to calculate two photon patterns for the purpose of training the network. We show as a proof of concept that a deep neural. 1 1ecole polytechnique fédérale de lausanne laboratory of applied photonics devices ch 1015 lausanne switzerland.

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. Multimode fibers mmf are an example of a highly scattering medium which scramble the coherent light propagating within them and produce seemingly random patterns. We were able to demonstrate this result for fibers up to 1 km long by training the dnns with a database of 16 000 handwritten digits. Multimode optical fiber transmission with a deep learning network article pdf available in light.

Multimode optical fiber transmission with a deep learning network babak rahmani 1 2damien loterie 1 georgia konstantinou 1 demetri psaltis christophe moser 1ecole polytechnique fédérale de lausanne laboratory of applied photonics devices ch 1015 lausanne switzerland 2ecole polytechnique fédérale de lausanne laboratory of optics ch 1015 lausanne switzerland. Multimode fibers mmfs are an example of a highly scattering medium which scramble the coherent light propagating within them to produce seemingly random patterns. We show as a proof of concept that a deep learning neural. Multimode optical fiber transmission with a deep learning network.

Thus for applications such as imaging and image projection through a mmf careful measurements of the relationship between inputs and outputs of the fiber are required. Deep neural networks dnns are used to classify and reconstruct the input images from the intensity of the speckle patterns that result after the inputs are propagated through multimode fiber mmf. Deep learning networks have been employed earlier for imaging through multimode fibers but the large amount of data required for training the network was an obstacle. Rahmani b 1 loterie d 1 konstantinou g 1 psaltis d 2 moser c 1.

We experimentally show that the spectrum of the light at the output of the fiber can be tailored by a trained deep neural network.