EUVIMEDEUVIMED entdecken
Open Access

Brain‐Inspired In‐Memory Data Pruning and Computing with TaO x Mem‐Selectors

Yi Li, Jinru Lai, Songqi Wang, Ning Lin, Xu Zheng, Wenxuan Sun, Danian Dong, Xiqing Xu, Haili Ma, Feng Zhang, Xiaojuan Qi, Zhongrui Wang iD und 4 weitere

Advanced Materials · 2025-10 · 37 (43)

DOI: 10.1002/adma.202502168 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 25.08.2025. Verfasst von Yi Li und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, 999077, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Youth Innovation Promotion Association CAS, Hong Kong Innovation and Technology Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The selective attention mechanisms inherent in the human visual system provide a promising framework for developing edge systems that can simultaneously prune and process critical information from visual input. However, conventional complementary metal‐oxide‐semiconductor‐based edge vision systems rely on complex digital logic for data pruning, alongside the physical separation of pruning, memory, and processing. This increases both power consumption and latency. Herein, a Mem‐Selector (M‐S) device that features reconfigurable non‐volatile resistive memory and volatile threshold switching in a Ta/TaO x /Ta 2 O 5 stack is presented. For the first time, using transmission electron microscopy, the formation and rupture of conductive oxygen vacancy filaments are observed when the device operates as a resistive memory, as well as the growth of Ta‐rich nanocrystalline clusters when it switches to threshold mode. This suggests the coexistence of ionic and electronic switching mechanisms. By leveraging a multifunctional M‐S device, an in‐memory pruning‐computing (IMPC) system that simultaneously prunes and processes information is constructed. The IMPC system, inspired by human visual‐selective attention, the IMPC system adaptively extracts essential information while pruning trivial inputs based on task complexity. This approach optimizes the balance between hardware cost and classification performance. Compared to conventional in‐memory computing systems, the integrated IMPC system reduces input energy consumption by 29%, 54%, and 90% with less than 1% accuracy loss. Additionally, it shows robustness improvements of 7.6%, 29.8%, and 80.7% on the CIFAR‐10, FashionMNIST, and MNIST datasets, respectively. This demonstrates the potential of hardware‐software co‐design for energy‐efficient, high‐performance edge hardware.

Schlagwörter

Stichwörter der Autor:innen

data pruningin‐memory computingmemristorneuromorphic computing

Autor:innen und Institutionen

  • Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, 999077, China.
  • School of Microelectronics, Southern University of Science and Technology, Shenzhen, 518055, China.
  • Center for Advanced Semiconductor and Integrated Circuit, The University of Hong Kong, Hong Kong SAR, 999077, China.
  • State Key Lab of Fabrication Technologies for Integrated Circuits, Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, 100029, China.
  • School of Microelectronics, University of Science and Technology of China, Hefei, 230026, China.
  • Key Laboratory of Fabrication Technologies for Integrated Circuits, Chinese Academy of Sciences, Beijing, 100029, China.

ORCID-Profile: Zhongrui Wang

Förderung

  • National Natural Science Foundation of China
  • Youth Innovation Promotion Association CAS
  • Hong Kong Innovation and Technology Fund
  • Shenzhen Science and Technology Innovation Commission
  • Hong Kong Research Grant Council
  • Youth Innovation Promotion Association of the Chinese Academy of Sciences
  • Science, Technology and Innovation Commission of Shenzhen Municipality

Zitieren

APA

Li, Y., Lai, J., Wang, S., Lin, N., Zheng, X., Sun, W., Dong, D., Xu, X., Ma, H., Zhang, F., Qi, X., Wang, Z., Xu, X., Shang, D., Wang, H., & Liu, M. (2025). Brain‐Inspired In‐Memory Data Pruning and Computing with TaO x Mem‐Selectors. Advanced Materials, 37(43). https://doi.org/10.1002/adma.202502168

Vancouver

Li Y, Lai J, Wang S, Lin N, Zheng X, Sun W, et al. Brain‐Inspired In‐Memory Data Pruning and Computing with TaO x Mem‐Selectors. Advanced Materials. 2025;37(43). doi:10.1002/adma.202502168

BibTeX
@article{Li2025,
  author = {Li, Yi and Lai, Jinru and Wang, Songqi and Lin, Ning and Zheng, Xu and Sun, Wenxuan and Dong, Danian and Xu, Xiqing and Ma, Haili and Zhang, Feng and Qi, Xiaojuan and Wang, Zhongrui and Xu, Xiaoxin and Shang, Dashan and Wang, Han and Liu, Ming},
  title = {Brain‐Inspired In‐Memory Data Pruning and Computing with TaO x Mem‐Selectors},
  journal = {Advanced Materials},
  year = {2025},
  volume = {37},
  number = {43},
  doi = {10.1002/adma.202502168}
}
Kostenlos starten →