Diffractive neural networks for mode-sorting with flexible detection regions

2025/08/27 by Bearne, Kaden, Duplinskiy, Alexander, Filipovich, Matthew J. +1 · 1 citation
#FOS: Physical sciences #Optics (physics.optics)

paper · doi:10.48550/arxiv.2508.20058

Abstract

Mode-sorting is a procedure that decomposes a light field into a basis of transverse modes, directing each mode into a separate spatial location, allowing the constituent mode intensities to be measured simultaneously. We demonstrate a mode-sorter based on a diffractive optical neural network and show that it is advantageous to include the output detection regions into the trainable set of parameters of that network. This approach outperforms traditional mode-sorting methods, achieving higher efficiency for the same crosstalk levels.

Citations

• TorchOptics: An open-source Python library for differentiable Fourier optics simulations
• Tsang's resolution enhancement method for imaging with focused illumination
• Tsang’s resolution enhancement method for imaging with focused illumination
• A physical neural network training approach toward multi-plane light conversion design
• High-dimensional spatial mode sorting and optical circuit design using multi-plane light conversion
• All-optical machine learning using diffractive deep neural networks

Cited by

• Miniaturised transmissive multi-plane light converters via laser-written geometric phase holograms cascaded in glass

Related

• Orthogonality of Diffractive Deep Neural Networks
• Design of diffractive neural networks solving different classification problems at different wavelengths
• Intelligent Mode Sorting in Turbulence with Task-Dependent Optical Neural Networks
• An optical diffractive deep neural network with multiple frequency-channels
• Physically interpretable diffractive optical networks for high-dimensional vortex mode sorting