Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing
Advanced Materials · 2025-01 · 37 (2)
DOI: 10.1002/adma.202312783 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 29.10.2024. Verfasst von Jingfang Pei und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N. T., Hong Kong SAR, 999077, China. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: CUHK, RGC, PolyU.
Abstract (Originalsprache)
Neural networks as a core information processing technology in machine learning and artificial intelligence demand substantial computational resources to deal with the extensive multiply‐accumulate operations. Neuromorphic computing is an emergent solution to address this problem, allowing the computation performed in memory arrays in parallel with high efficiencies conforming to the neural networks. Here, scalable synaptic transistor memories are developed from solution‐sorted carbon nanotubes. The transistors exhibit a large switching ratio of over 10 5 , a significant memory window of ≈12 V arising from charge trapping, and low response delays down to tens of nanoseconds. These device characteristics endow highly stabilized reconfigurable conductance states, successful emulation of synaptic functions, and a high data processing speed. Importantly, the devices exhibit uniform characteristic metrics, e.g., with a 1.8% variation in the memory window, suggesting an industrial‐scale manufacturing capability of the fabrication. Using the memories, a hardware convolution kernel is designed and parallel image processing is demonstrated at a speed of 1 M bit per second per input channel. Given the efficacy of the convolution kernel, a promising prospect of the memories in implementing neuromorphic computing is envisaged. To explore the potential, large‐scale convolution kernels are simulated and high‐speed video processing is realized for autonomous driving.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N. T., Hong Kong SAR, 999077, China.
- Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, 518055, China.
- Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong, Shatin, N. T., Hong Kong SAR, 999077, China.
- School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, 100191, China.
- Department of Applied Physics, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, 999077, China.
ORCID-Profile: Jingfang Pei, Lekai Song, Pengyu Liu, Songwei Liu, Yingyi Wen, Yang Liu, Xiaolong Chen, Teng Ma, Shuo Gao, Guohua Hu
Förderung
- CUHK
- RGC
- PolyU
- NSFC
- SHIAE
- Chinese University of Hong Kong
- Hong Kong Polytechnic University
- National Natural Science Foundation of China
Zitieren
APA
Pei, J., Song, L., Liu, P., Liu, S., Liang, Z., Wen, Y., Liu, Y., Wang, S., Chen, X., Ma, T., Gao, S., & Hu, G. (2025). Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing. Advanced Materials, 37(2). https://doi.org/10.1002/adma.202312783
Vancouver
Pei J, Song L, Liu P, Liu S, Liang Z, Wen Y, et al. Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing. Advanced Materials. 2025;37(2). doi:10.1002/adma.202312783
BibTeX
@article{Pei2025,
author = {Pei, Jingfang and Song, Lekai and Liu, Pengyu and Liu, Songwei and Liang, Zihan and Wen, Yingyi and Liu, Yang and Wang, Shengbo and Chen, Xiaolong and Ma, Teng and Gao, Shuo and Hu, Guohua},
title = {Scalable Synaptic Transistor Memory from Solution‐Processed Carbon Nanotubes for High‐Speed Neuromorphic Data Processing},
journal = {Advanced Materials},
year = {2025},
volume = {37},
number = {2},
doi = {10.1002/adma.202312783}
}
EUVIMED