Multi-functional broadband diffractive neural network with a single spatial light modulator
Diffractive neural networks (DNNs) are emerging as a novel optical computing architecture that combines wave optics with deep-learning methods for high-speed parallel information processing. Herein, we report a reflection type, multi-functional, broadband DNN design. It consists of two phase-modulat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-01-01
|
| Series: | APL Photonics |
| Online Access: | http://dx.doi.org/10.1063/5.0245832 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542789151227904 |
|---|---|
| author | Bolin Li Yinfei Zhu Jinlei Fei Runshi Zheng Min Gu Jian Lin |
| author_facet | Bolin Li Yinfei Zhu Jinlei Fei Runshi Zheng Min Gu Jian Lin |
| author_sort | Bolin Li |
| collection | DOAJ |
| description | Diffractive neural networks (DNNs) are emerging as a novel optical computing architecture that combines wave optics with deep-learning methods for high-speed parallel information processing. Herein, we report a reflection type, multi-functional, broadband DNN design. It consists of two phase-modulation layers based on a single spatial light modulator and a mirror facing it. The power efficiency of this design is more than 16 times higher than that of the cascaded structure utilizing beam splitters. It can function either as a two-layer DNN or a one-layer DNN with the other serving as an information input layer. Single- and dual-wavelength filtering and focusing, as well as spatial wavelength demultiplexing of supercontinuum, are experimentally demonstrated using the two-layer DNN, whereas the one-layer DNN is experimentally demonstrated by the classification of hand-written digits, which are input by the first layer via holographic imaging. The designed DNN could operate independently or be readily integrated with other optical systems and may find applications in spectroscopy, microscopy, and information technology. |
| format | Article |
| id | doaj-art-7bd0384e115d4961b0f86a37e0cd1442 |
| institution | Kabale University |
| issn | 2378-0967 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Photonics |
| spelling | doaj-art-7bd0384e115d4961b0f86a37e0cd14422025-02-03T16:36:22ZengAIP Publishing LLCAPL Photonics2378-09672025-01-01101016115016115-910.1063/5.0245832Multi-functional broadband diffractive neural network with a single spatial light modulatorBolin Li0Yinfei Zhu1Jinlei Fei2Runshi Zheng3Min Gu4Jian Lin5School of Artificial Intelligence Science and Technology, University of Shanghai for Science and Technology, Shanghai, ChinaInstitute of Photonic Chips, University of Shanghai for Science and Technology, Shanghai, ChinaInstitute of Photonic Chips, University of Shanghai for Science and Technology, Shanghai, ChinaSchool of Artificial Intelligence Science and Technology, University of Shanghai for Science and Technology, Shanghai, ChinaSchool of Artificial Intelligence Science and Technology, University of Shanghai for Science and Technology, Shanghai, ChinaSchool of Artificial Intelligence Science and Technology, University of Shanghai for Science and Technology, Shanghai, ChinaDiffractive neural networks (DNNs) are emerging as a novel optical computing architecture that combines wave optics with deep-learning methods for high-speed parallel information processing. Herein, we report a reflection type, multi-functional, broadband DNN design. It consists of two phase-modulation layers based on a single spatial light modulator and a mirror facing it. The power efficiency of this design is more than 16 times higher than that of the cascaded structure utilizing beam splitters. It can function either as a two-layer DNN or a one-layer DNN with the other serving as an information input layer. Single- and dual-wavelength filtering and focusing, as well as spatial wavelength demultiplexing of supercontinuum, are experimentally demonstrated using the two-layer DNN, whereas the one-layer DNN is experimentally demonstrated by the classification of hand-written digits, which are input by the first layer via holographic imaging. The designed DNN could operate independently or be readily integrated with other optical systems and may find applications in spectroscopy, microscopy, and information technology.http://dx.doi.org/10.1063/5.0245832 |
| spellingShingle | Bolin Li Yinfei Zhu Jinlei Fei Runshi Zheng Min Gu Jian Lin Multi-functional broadband diffractive neural network with a single spatial light modulator APL Photonics |
| title | Multi-functional broadband diffractive neural network with a single spatial light modulator |
| title_full | Multi-functional broadband diffractive neural network with a single spatial light modulator |
| title_fullStr | Multi-functional broadband diffractive neural network with a single spatial light modulator |
| title_full_unstemmed | Multi-functional broadband diffractive neural network with a single spatial light modulator |
| title_short | Multi-functional broadband diffractive neural network with a single spatial light modulator |
| title_sort | multi functional broadband diffractive neural network with a single spatial light modulator |
| url | http://dx.doi.org/10.1063/5.0245832 |
| work_keys_str_mv | AT bolinli multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator AT yinfeizhu multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator AT jinleifei multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator AT runshizheng multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator AT mingu multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator AT jianlin multifunctionalbroadbanddiffractiveneuralnetworkwithasinglespatiallightmodulator |