Piezoelectric surface acoustic wave memristor neural network
Science Advances · 23.01.2026 · 12 (4)
DOI: 10.1126/sciadv.adx6227 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 23.01.2026. Verfasst von Yi Zhang und 16 weiteren Autor:innen. Beteiligte Einrichtung: School of Microelectronics, Southern University of Science and Technology, Shenzhen 518055, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Commission, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Processing wireless RF signals using analog electromagnetic (EM) wave-based neural networks enables energy efficiency and parallelism by integrating sensing, memory, and computation, avoiding analog-to-digital conversions (ADCs) and the von-Neumann bottleneck. Yet, a notable challenge remains: the absence of compact and programmable building blocks for EM wave-based neural networks. To overcome this limitation, we propose a piezoelectric surface acoustic wave (SAW) memristor that integrates an Ag/SiO 2 /Au memristor with an acoustoelectric phase shifter. Operating at shorter wavelengths than EM waves, it offers a compact footprint and encodes tunable neural network parameters via nonvolatile programmability and the acoustoelectric effect. A proof-of-concept SAW memristor neural network was experimentally demonstrated on a vector classification task, achieving 91.7% accuracy on par with software while reducing footprint by 10 5 times versus EM systems and energy consumption by 37 times versus digital systems. This work paves the way for compact, energy-efficient RF signal processing at the edge.
Autor:innen und Institutionen
- School of Microelectronics, Southern University of Science and Technology, Shenzhen 518055, China.
- Department of Electrical and Electronic Engineering, The University of Hong Kong, Lung Fu Shan, Hong Kong.
- School of Integrated Circuits, Shenzhen Polytechnic University, Shenzhen 518055, China.
- Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong.
- ACCESS-AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Ma Liu Shui, Hong Kong.
- School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen 518055, China.
ORCID-Profile: Yi Zhang, Yi Deng, Dingchen Wang, Yang Jiang, Shaocong Wang, Mujun Li, Xiaohui Wang, Fangzhou Du, Qiaoyu Hu, Xiaojuan Qi, Han Wang, Qing Wang, Hongyu Yu, Zhongrui Wang
Förderung
- National Natural Science Foundation of China
- Shenzhen Science and Technology Innovation Commission
- Beijing Natural Science Foundation
- Hong Kong Research Grant Council
- Research on mechanism of source/drain ohmic contact and the related GaN p-FET
- Research on high-reliable GaN power device and the related industrial power system
- National key R&D program of China
- Institute of Advanced Manufacturing and Application of Integrated Circuits
Zitieren
APA
Zhang, Y., Deng, Y., Wang, D., Xiong, Z., Jiang, Y., Deng, C., Tang, C., Wang, S., Li, M., Wang, X., Du, F., Hu, Q., Qi, X., Wang, H., Wang, Q., Yu, H., & Wang, Z. (2026). Piezoelectric surface acoustic wave memristor neural network. Science Advances, 12(4). https://doi.org/10.1126/sciadv.adx6227
Vancouver
Zhang Y, Deng Y, Wang D, Xiong Z, Jiang Y, Deng C, et al. Piezoelectric surface acoustic wave memristor neural network. Science Advances. 2026;12(4). doi:10.1126/sciadv.adx6227
BibTeX
@article{Zhang2026,
author = {Zhang, Yi and Deng, Yi and Wang, Dingchen and Xiong, Zilong and Jiang, Yang and Deng, Chenkai and Tang, Chuying and Wang, Shaocong and Li, Mujun and Wang, Xiaohui and Du, Fangzhou and Hu, Qiaoyu and Qi, Xiaojuan and Wang, Han and Wang, Qing and Yu, Hongyu and Wang, Zhongrui},
title = {Piezoelectric surface acoustic wave memristor neural network},
journal = {Science Advances},
year = {2026},
volume = {12},
number = {4},
doi = {10.1126/sciadv.adx6227}
}
EUVIMED