A Memristor‐Based Saturation‐Constrained Information Capacity Framework for Temporal Information Processing
Advanced Materials · 2026-11 · 38 (62)
DOI: 10.1002/adma.75096 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 20.09.2026. Verfasst von Wenbin Guo und 14 weiteren Autor:innen. Beteiligte Einrichtung: School of Integrated Circuits, Anhui University, Hefei, Anhui, China. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Innovation Research Foundation of National University of Defense Technology.
Abstract (Originalsprache)
Physical reservoir computing (PRC) has emerged as a highly energy‐efficient paradigm for processing high‐dimensional spatiotemporal data in edge‐intelligent systems. However, the deployment of PRC is often limited by the quantization mismatch between continuous input signals and the finite dynamic range of hardware substrates. Conventional binary time‐multiplexing ensures high noise immunity but necessitates protracted pulse sequences that induce high latency and premature physical saturation. Conversely, multi‐valued analog encoding enhances information density but frequently induces state overlap, operating devoid of physical quantization boundaries. To resolve this physical‐information trade‐off, we propose a saturation‐constrained information capacity (SCIC) framework. This framework considers task‐specific encoding variables and substrate‐intrinsic constraints, enabling device‐informed optimization of input mapping. We experimentally demonstrate this framework on a highly uniform, selector‐free 32 × 32 crossbar array, utilizing the volatile dynamics of memristors. Under the experimentally selected encoding conditions, the SCIC‐guided RC achieves exceptional performance in temporal prediction (NRMSE of 0.019), speech recognition (free‐spoken digit dataset (FSDD) subset accuracy of ∼94.5%), and real‐time obstacle avoidance. Our approach links encoding constraints to solid‐state device physics, providing a device‐informed method for PRC parameterization at the edge.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Integrated Circuits, Anhui University, Hefei, Anhui, China.
- College of Electronic Science and Technology, National University of Defense Technology, Changsha, China.
- School of Microelectronics, University of Science and Technology of China, Hefei, Anhui, China.
- Frontier Institute of Chip and System, Fudan University, Shanghai, China.
ORCID-Profile: Wenbin Guo, Zuheng Wu, Haochen Wang, Wei Wang, Xiaolong Zhao, Rongrong Cao, Yunlai Zhu, Zuyu Xu, Yuehua Dai, Xumeng Zhang
Förderung
- National Natural Science Foundation of China
- National Key R&D Program of China
- Innovation Research Foundation of National University of Defense Technology
- Anhui Provincial Natural Science Foundation under
Zitieren
APA
Guo, W., Wu, Z., Wang, H., Zou, J., Hao, Y., Wang, W., Zhao, X., Cao, R., Feng, Z., Xu, L., Lu, W., Zhu, Y., Xu, Z., Dai, Y., & Zhang, X. (2026). A Memristor‐Based Saturation‐Constrained Information Capacity Framework for Temporal Information Processing. Advanced Materials, 38(62). https://doi.org/10.1002/adma.75096
Vancouver
Guo W, Wu Z, Wang H, Zou J, Hao Y, Wang W, et al. A Memristor‐Based Saturation‐Constrained Information Capacity Framework for Temporal Information Processing. Advanced Materials. 2026;38(62). doi:10.1002/adma.75096
BibTeX
@article{Guo2026,
author = {Guo, Wenbin and Wu, Zuheng and Wang, Haochen and Zou, Jianxun and Hao, Yunxia and Wang, Wei and Zhao, Xiaolong and Cao, Rongrong and Feng, Zhe and Xu, Lihua and Lu, Wendong and Zhu, Yunlai and Xu, Zuyu and Dai, Yuehua and Zhang, Xumeng},
title = {A Memristor‐Based Saturation‐Constrained Information Capacity Framework for Temporal Information Processing},
journal = {Advanced Materials},
year = {2026},
volume = {38},
number = {62},
doi = {10.1002/adma.75096}
}
EUVIMED