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

Rahmani, Babak; Loterie, Damien; Kakkava, Eirini; Borhani, Navid; Teğin, Uğur; Psaltis, Demetri; Moser, Christophe

doi:10.1038/s42256-020-0199-9

Cited by 72 publications

(54 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks (CNNs) have been applied to the MMF image reconstruction problem by several recent authors [17][18][19][20][21][22] . Here, we employ the U-Net architecture, which Rahmani et al have previously used for MMF image reconstruction with the MNIST digit dataset 18 .…”

Section: Methodsmentioning

confidence: 99%

“…This would not require additional interferometric equipment, and can potentially scale up to large image sizes. The idea was proposed and investigated decades ago [14][15][16] , but only in recent years has it been shown to perform well for reconstructing images of reasonable complexity [17][18][19][20][21] , aided by improvements in computational power and NN software.…”

mentioning

confidence: 99%

“…These recent advances in NN-aided MMF image reconstruction have focused on deep convolutional neural networks (CNNs) [17][18][19][20][21][22] . Unlike traditional dense NNs 23 , CNNs use convolution operations instead of general matrix multiplication within the NN layers 24 , inspired by biological processes in visual perception.…”

mentioning

confidence: 99%

“…This paper investigates the performance of dense NNs and CNNs for MMF image reconstruction. Whereas the earliest papers on NN-aided MMF image reconstruction used dense NNs [14][15][16] , most recent studies have concentrated on using CNNs [17][18][19][20][21][22] . (One exception to this trend was the study by Turpin et al of both dense NNs and CNNs for transmission control in scattering media and MMFs 28 .…”

mentioning

confidence: 99%

See 3 more Smart Citations

Image reconstruction through a multimode fiber with a simple neural network architecture

Zhu

Chan

Wang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Multimode fibers (MMFs) have the potential to carry complex images for endoscopy and related applications, but decoding the complex speckle patterns produced by mode-mixing and modal dispersion in MMFs is a serious challenge. Several groups have recently shown that convolutional neural networks (CNNs) can be trained to perform high-fidelity MMF image reconstruction. We find that a considerably simpler neural network architecture, the single hidden layer dense neural network, performs at least as well as previously-used CNNs in terms of image reconstruction fidelity, and is superior in terms of training time and computing resources required. The trained networks can accurately reconstruct MMF images collected over a week after the cessation of the training set, with the dense network performing as well as the CNN over the entire period.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Image reconstruction through a multimode fiber with a simple neural network architecture

Zhu

Chan

Wang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…It should be remembered, that the DenseNet has been trained only with synthetic data and works in an experimental environment successfully. The predicted mode weights can be further used for a robust control [38], which is commonly performed in imaging applications based on a field programmable gate array [10], [39].…”

Section: Experimental Investigationsmentioning

confidence: 99%

Intensity-Only Mode Decomposition on Multimode Fibers Using a Densely Connected Convolutional Network

Rothe

Zhang

Koukourakis

et al. 2021

J. Lightwave Technol.

View full text Add to dashboard Cite

Image Transmission Through a Dynamically Perturbed Multimode Fiber by Deep Learning

Resisi

Popoff

Bromberg

2021

Laser & Photonics Reviews

View full text Add to dashboard Cite

When multimode optical fibers are perturbed, the data that is transmitted through them is scrambled. This presents a major difficulty for many possible applications, such as multimode fiber based telecommunication and endoscopy. To overcome this challenge, a deep learning approach that generalizes over mechanical perturbations is presented. Using this approach, successful reconstruction of the input images from intensity‐only measurements of speckle patterns at the output of a 1.5 m‐long randomly perturbed multimode fiber is demonstrated. The model's success is explained by hidden correlations in the speckle of random fiber conformations.

show abstract

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

Cited by 72 publications

References 35 publications

Image reconstruction through a multimode fiber with a simple neural network architecture

Image reconstruction through a multimode fiber with a simple neural network architecture

Intensity-Only Mode Decomposition on Multimode Fibers Using a Densely Connected Convolutional Network

Image Transmission Through a Dynamically Perturbed Multimode Fiber by Deep Learning

Contact Info

Product

Resources

About