A Simple Optical Convolution Strategy Based on Versatile Adjustable Optical Convolution Kernel for All‐Optical Convolution Computing
Advanced Materials · 2025-07 · 37 (27)
DOI: 10.1002/adma.202420534 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 23.04.2025. Verfasst von Liuting Shan und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Optoelectronic Display, National & Local United Engineering Lab of Flat Panel Display Technology, Fuzhou University, Fuzhou, 350002, P. …. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Convolutional neural network (CNN) is currently one of the most important artificial neural networks. However, traditional CNN hardware architectures suffer from significant increases in energy consumption and processing time as the demand for artificial intelligence tasks grows. Here, a novel optical convolution computing strategy is proposed that leverages a continuously adjustable photoluminescent device (CA‐PLD) as the optical convolution kernel, enabling parallel, all‐optical convolution computing and greatly simplifying the traditional convolution process. Under ultraviolet illumination, the CA‐PLD exhibits visible long‐afterglow emission characteristics due to the charge trapping and retention effects. This allows for continuously adjustable light weights, facilitating arbitrary convolution operations. Building on this, parallel and efficient multiply‐accumulate operations have been successfully demonstrated using CA‐PLD arrays with different weight combinations. Moreover, space‐transformable CA‐PLD units enable applications in dilated convolution. In a semantic segmentation task with 20 categories, the CA‐PLD units achieve higher Intersection over Union (IoU) values and accuracy. Therefore, the weight‐adjustable and spatial transformable CA‐PLD proposed in this work holds promise for future applications in intelligent optical computing systems and optical implementations of non‐von Neumann architectures.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Optoelectronic Display, National & Local United Engineering Lab of Flat Panel Display Technology, Fuzhou University, Fuzhou, 350002, P. R. China.
- Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, Fuzhou, 350100, P. R. China.
- School of Physics and Electronic Technology, Liaoning Normal University, Dalian, 116029, P. R. China.
- College of Materials Science and Engineering, Key Laboratory of Automobile Materials, Ministry of Education, Jilin University, Changchun, 130012, P. R. China.
ORCID-Profile: Huipeng Chen
Förderung
- Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China
- National Natural Science Foundation of China
Zitieren
APA
Shan, L., Xu, C., Pan, J., Lu, W., Ma, X., Liu, D., Shi, C., Du, T., Zhang, J., & Chen, H. (2025). A Simple Optical Convolution Strategy Based on Versatile Adjustable Optical Convolution Kernel for All‐Optical Convolution Computing. Advanced Materials, 37(27). https://doi.org/10.1002/adma.202420534
Vancouver
Shan L, Xu C, Pan J, Lu W, Ma X, Liu D, et al. A Simple Optical Convolution Strategy Based on Versatile Adjustable Optical Convolution Kernel for All‐Optical Convolution Computing. Advanced Materials. 2025;37(27). doi:10.1002/adma.202420534
BibTeX
@article{Shan2025,
author = {Shan, Liuting and Xu, Chenhui and Pan, Jianyong and Lu, Wenjie and Ma, Xiao and Liu, Di and Shi, Chunyan and Du, Tingting and Zhang, Jiaqi and Chen, Huipeng},
title = {A Simple Optical Convolution Strategy Based on Versatile Adjustable Optical Convolution Kernel for All‐Optical Convolution Computing},
journal = {Advanced Materials},
year = {2025},
volume = {37},
number = {27},
doi = {10.1002/adma.202420534}
}
EUVIMED