Pre-sensor computing with compact multilayer optical neural network
Science Advances · 26.07.2024 · 10 (30)
DOI: 10.1126/sciadv.ado8516 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 26.07.2024. Verfasst von Zheng Huang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Moving computation units closer to sensors is becoming a promising approach to addressing bottlenecks in computing speed, power consumption, and data storage. Pre-sensor computing with optical neural networks (ONNs) allows extensive processing. However, the lack of nonlinear activation and dependence on laser input limits the computational capacity, practicality, and scalability. A compact and passive multilayer ONN (MONN) is proposed, which has two convolution layers and an inserted nonlinear layer, performing pre-sensor computations with designed passive masks and a quantum dot film for incoherent light. MONN has an optical length as short as 5 millimeters, two orders of magnitude smaller than state-of-the-art lens-based ONNs. MONN outperforms linear single-layer ONN across various vision tasks, off-loading up to 95% of computationally expensive operations into optics from electronics. Motivated by MONN, a paradigm is emerging for mobile vision, fulfilling the demands for practicality, miniaturization, and low power consumption.
Autor:innen und Institutionen
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
- Beijing National Research Center for Information Science and Technology, Beijing 100084, China.
ORCID-Profile: Zheng Huang, Wanxin Shi, Shukai Wu, Yaode Wang, Sigang Yang, Hongwei Chen
Zitieren
APA
Huang, Z., Shi, W., Wu, S., Wang, Y., Yang, S., & Chen, H. (2024). Pre-sensor computing with compact multilayer optical neural network. Science Advances, 10(30). https://doi.org/10.1126/sciadv.ado8516
Vancouver
Huang Z, Shi W, Wu S, Wang Y, Yang S, Chen H. Pre-sensor computing with compact multilayer optical neural network. Science Advances. 2024;10(30). doi:10.1126/sciadv.ado8516
BibTeX
@article{Huang2024,
author = {Huang, Zheng and Shi, Wanxin and Wu, Shukai and Wang, Yaode and Yang, Sigang and Chen, Hongwei},
title = {Pre-sensor computing with compact multilayer optical neural network},
journal = {Science Advances},
year = {2024},
volume = {10},
number = {30},
doi = {10.1126/sciadv.ado8516}
}
EUVIMED