All-optical Fourier neural network using partially coherent light

Optical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption. While coherent light is conventionally used in optical neural networks, our study proposed harnessing spatially incoherent light in all-op...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianwei Qin, Yanbing Liu, Yan Liu, Xun Liu, Wei Li, Fangwei Ye
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Chip
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2709472325000140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320634241253376
author Jianwei Qin
Yanbing Liu
Yan Liu
Xun Liu
Wei Li
Fangwei Ye
author_facet Jianwei Qin
Yanbing Liu
Yan Liu
Xun Liu
Wei Li
Fangwei Ye
author_sort Jianwei Qin
collection DOAJ
description Optical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption. While coherent light is conventionally used in optical neural networks, our study proposed harnessing spatially incoherent light in all-optical Fourier neural networks. Contrary to natural predictions of declining target recognition accuracy with increased incoherence, our experimental results demonstrated a surprising outcome: improved accuracy with incoherent light. We attribute this enhancement to spatially incoherent light's ability to alleviate experimental errors like diffraction rings and laser speckle. Our experiments introduced controllable spatial incoherence by passing monochromatic light through a spatial light modulator featuring a dynamically changing random phase array. These findings underscore partially coherent light's potential to optimize optical neural networks, delivering dependable and efficient solutions for applications demanding consistent accuracy and robustness across diverse conditions, including on-chip optical computing, photonic interconnects, and reconfigurable optical processors.
format Article
id doaj-art-35fa423394c648e39daa24bc7c6d096f
institution Kabale University
issn 2709-4723
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Chip
spelling doaj-art-35fa423394c648e39daa24bc7c6d096f2025-08-20T03:50:01ZengElsevierChip2709-47232025-09-014310014010.1016/j.chip.2025.100140All-optical Fourier neural network using partially coherent lightJianwei Qin0Yanbing Liu1Yan Liu2Xun Liu3Wei Li4Fangwei Ye5School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, ChinaBeijing Institute of Space Mechanics and Electricity, China Academy of Space Technology, Beijing 100094, ChinaBeijing Institute of Space Mechanics and Electricity, China Academy of Space Technology, Beijing 100094, China; Corresponding authors.School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, China; School of Physics, Chengdu University of Technology, Chengdu 610059, China; Corresponding authors.Optical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption. While coherent light is conventionally used in optical neural networks, our study proposed harnessing spatially incoherent light in all-optical Fourier neural networks. Contrary to natural predictions of declining target recognition accuracy with increased incoherence, our experimental results demonstrated a surprising outcome: improved accuracy with incoherent light. We attribute this enhancement to spatially incoherent light's ability to alleviate experimental errors like diffraction rings and laser speckle. Our experiments introduced controllable spatial incoherence by passing monochromatic light through a spatial light modulator featuring a dynamically changing random phase array. These findings underscore partially coherent light's potential to optimize optical neural networks, delivering dependable and efficient solutions for applications demanding consistent accuracy and robustness across diverse conditions, including on-chip optical computing, photonic interconnects, and reconfigurable optical processors.http://www.sciencedirect.com/science/article/pii/S2709472325000140Partially coherent lightOptical neural network
spellingShingle Jianwei Qin
Yanbing Liu
Yan Liu
Xun Liu
Wei Li
Fangwei Ye
All-optical Fourier neural network using partially coherent light
Chip
Partially coherent light
Optical neural network
title All-optical Fourier neural network using partially coherent light
title_full All-optical Fourier neural network using partially coherent light
title_fullStr All-optical Fourier neural network using partially coherent light
title_full_unstemmed All-optical Fourier neural network using partially coherent light
title_short All-optical Fourier neural network using partially coherent light
title_sort all optical fourier neural network using partially coherent light
topic Partially coherent light
Optical neural network
url http://www.sciencedirect.com/science/article/pii/S2709472325000140
work_keys_str_mv AT jianweiqin allopticalfourierneuralnetworkusingpartiallycoherentlight
AT yanbingliu allopticalfourierneuralnetworkusingpartiallycoherentlight
AT yanliu allopticalfourierneuralnetworkusingpartiallycoherentlight
AT xunliu allopticalfourierneuralnetworkusingpartiallycoherentlight
AT weili allopticalfourierneuralnetworkusingpartiallycoherentlight
AT fangweiye allopticalfourierneuralnetworkusingpartiallycoherentlight