High-frame-rate reconfigurable diffractive neural network based on superpixels

The existing implementations of reconfigurable diffractive neural networks rely on both a liquid-crystal spatial light modulator and a digital micromirror device, which results in complexity in the alignment of the optical system and a constrained computational speed. Here, we propose a superpixel d...

Full description

Saved in:
Bibliographic Details
Published in:Optics letters 2023-10, Vol.48 (19), p.5025-5028
Main Authors: Qu, Yuan, Lian, Hengyu, Ding, Chunxu, Liu, Huazhen, Liu, Linxian, Yang, Jiamiao
Format: Article
Language:English
Subjects:
Data processing
Neural networks
Reconfiguration
Spatial light modulators
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The existing implementations of reconfigurable diffractive neural networks rely on both a liquid-crystal spatial light modulator and a digital micromirror device, which results in complexity in the alignment of the optical system and a constrained computational speed. Here, we propose a superpixel diffractive neural network that leverages solely a digital micromirror device to control the neuron bias and connection. This approach considerably simplifies the optical system and achieves a computational speed of 326 Hz per neural layer. We validate our method through experiments in digit classification, achieving an accuracy of 82.6%, and action recognition, attaining a perfect accuracy of 100%. Our findings demonstrate the effectiveness of the superpixel diffractive neural network in simplifying the optical system and enhancing computational speed, opening up new possibilities for real-time optical information processing applications.
ISSN:0146-9592
1539-4794
DOI:10.1364/OL.498712