An overhead-reduced, efficient, fully analog neural-network computing hardware
Science Advances · 24.10.2025 · 11 (43)
DOI: 10.1126/sciadv.adv7555 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 24.10.2025. Verfasst von Jiabao Ye und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of Integrated Circuits, Zhejiang University, Hangzhou 310058, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Human brain–inspired neural-network computing hardware has the potential to overcome the energy efficiency and resource overhead challenges caused by the von Neumann bottleneck. However, existing neural-network computing hardware still exhibits a considerable gap compared to the human brain, likely due to the absence of complex data compression functions and the fully analog domain operating strategy adopted by the brain. To solve these problems, a fully analog neural - network computing hardware (FANCH) with input data compression is proposed and fabricated at both the chip and system levels in this work. FANCH implements the complete computational process of the neural networks using fully analog circuits. FANCH achieves an accuracy with only a 0.36% reduction from the software baseline in the handwritten digit recognition task. FANCH demonstrates advantages in energy efficiency compared to state-of-the-art artificial intelligence acceleration chips and systems. Our work provides an efficient fully analog hardware solution for edge computing applications with low hardware resource demands.
Autor:innen und Institutionen
- College of Integrated Circuits, Zhejiang University, Hangzhou 310058, China.
- College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China.
- Hangzhou Research Institute, Xidian University, Hangzhou 311231, China.
- Zhejiang ICsprout Semiconductor Co., Ltd., Hangzhou 310058, China.
Zitieren
APA
Ye, J., Wang, W., Shi, C., Cui, X., Qu, W., Lin, P., Yu, X., Cheng, R., Wu, H., & Chen, B. (2025). An overhead-reduced, efficient, fully analog neural-network computing hardware. Science Advances, 11(43). https://doi.org/10.1126/sciadv.adv7555
Vancouver
Ye J, Wang W, Shi C, Cui X, Qu W, Lin P, et al. An overhead-reduced, efficient, fully analog neural-network computing hardware. Science Advances. 2025;11(43). doi:10.1126/sciadv.adv7555
BibTeX
@article{Ye2025,
author = {Ye, Jiabao and Wang, Wannian and Shi, Caiping and Cui, Xuecheng and Qu, Wanyuan and Lin, Peng and Yu, Xiao and Cheng, Ran and Wu, Hanming and Chen, Bing},
title = {An overhead-reduced, efficient, fully analog neural-network computing hardware},
journal = {Science Advances},
year = {2025},
volume = {11},
number = {43},
doi = {10.1126/sciadv.adv7555}
}
EUVIMED