Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material

Optical diffractive neural networks have sparked extensive research due to their low power consumption and high-speed capabilities in image processing. Here we propose and design a reconfigurable all-optical diffractive neural network structure with digital non-volatile optical neurons. The optical...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiaomu Hu, Jingyu Zhao, Chu Wu, Rui Zeng, Xiaobing Zhou, Shuang Zheng, Minming Zhang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10770557/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590420846051328
author Qiaomu Hu
Jingyu Zhao
Chu Wu
Rui Zeng
Xiaobing Zhou
Shuang Zheng
Minming Zhang
author_facet Qiaomu Hu
Jingyu Zhao
Chu Wu
Rui Zeng
Xiaobing Zhou
Shuang Zheng
Minming Zhang
author_sort Qiaomu Hu
collection DOAJ
description Optical diffractive neural networks have sparked extensive research due to their low power consumption and high-speed capabilities in image processing. Here we propose and design a reconfigurable all-optical diffractive neural network structure with digital non-volatile optical neurons. The optical neurons are built with Sb<sub>2</sub>Se<sub>3</sub> phase-change material and can switch between crystalline and amorphous states with no constant energy supply. Using three reconfigurable non-volatile digital diffractive layers and 10 photodetectors connected to a reconfigurable resistor network, our model achieves an accuracy of 94.46&#x0025; in the handwritten digit recognition task. Moreover, the fabrication and assembly robustness of the proposed optical diffractive neural network is verified through full-vector diffractive simulation. Thanks to its reconfigurability and low energy supply, the digital optical diffractive neural network holds great potential to facilitate a programmable and low-power-consumption photonic processor for optical-artificial-intelligence.
format Article
id doaj-art-bf62840f65b44ea5a237d1d9403bee1a
institution Kabale University
issn 1943-0655
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-bf62840f65b44ea5a237d1d9403bee1a2025-01-24T00:00:35ZengIEEEIEEE Photonics Journal1943-06552024-01-011661810.1109/JPHOT.2024.350805210770557Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change MaterialQiaomu Hu0https://orcid.org/0000-0001-6375-6161Jingyu Zhao1https://orcid.org/0009-0003-8790-671XChu Wu2Rui Zeng3Xiaobing Zhou4https://orcid.org/0009-0000-6599-3822Shuang Zheng5https://orcid.org/0000-0002-4825-5163Minming Zhang6https://orcid.org/0000-0002-3742-1445School of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaSchool of Optical and Electronic Information, Wuhan, ChinaOptical diffractive neural networks have sparked extensive research due to their low power consumption and high-speed capabilities in image processing. Here we propose and design a reconfigurable all-optical diffractive neural network structure with digital non-volatile optical neurons. The optical neurons are built with Sb<sub>2</sub>Se<sub>3</sub> phase-change material and can switch between crystalline and amorphous states with no constant energy supply. Using three reconfigurable non-volatile digital diffractive layers and 10 photodetectors connected to a reconfigurable resistor network, our model achieves an accuracy of 94.46&#x0025; in the handwritten digit recognition task. Moreover, the fabrication and assembly robustness of the proposed optical diffractive neural network is verified through full-vector diffractive simulation. Thanks to its reconfigurability and low energy supply, the digital optical diffractive neural network holds great potential to facilitate a programmable and low-power-consumption photonic processor for optical-artificial-intelligence.https://ieeexplore.ieee.org/document/10770557/Optical neural networksilicon photonicsphase change material
spellingShingle Qiaomu Hu
Jingyu Zhao
Chu Wu
Rui Zeng
Xiaobing Zhou
Shuang Zheng
Minming Zhang
Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
IEEE Photonics Journal
Optical neural network
silicon photonics
phase change material
title Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
title_full Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
title_fullStr Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
title_full_unstemmed Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
title_short Non-Volatile Reconfigurable Optical Digital Diffractive Neural Network Based on Phase Change Material
title_sort non volatile reconfigurable optical digital diffractive neural network based on phase change material
topic Optical neural network
silicon photonics
phase change material
url https://ieeexplore.ieee.org/document/10770557/
work_keys_str_mv AT qiaomuhu nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT jingyuzhao nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT chuwu nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT ruizeng nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT xiaobingzhou nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT shuangzheng nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial
AT minmingzhang nonvolatilereconfigurableopticaldigitaldiffractiveneuralnetworkbasedonphasechangematerial