A Novel Time‐Division Multiplexing Architecture Revealed by Reconfigurable Synapse for Deep Neural Networks

Y Yu‐Tao Li (School of Laboratory Medicine Hubei University of Chinese Medicine Wuhan 430065 China) K Kui Xu (Beijing Frontier Research Center for Biological Structures, State Key Laboratory of Membrane Biology, Tsinghua-Peking Joint Center for Life Sciences, School of Life Sciences, Tsinghua University) Y Yu‐Zhe Ma (Microelectronics Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou 511453 China) J Jun‐Ze Li (School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China) Y Yang Luo X Xin‐Ru Li (School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China) P Peng‐Hui Shen (School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China) L Lu‐Yu Zhao (School of Integrated Circuits and Electronics MIIT Key Laboratory for Low‐Dimensional Quantum Structure and Devices Beijing Institute of Technology Beijing 100081 China) H Hang Liu (Division of Life Science, The Hong Kong University of Science and Technology, Clear Water Bay) L Li Ren D De‐Hui Li (School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China) L Lian‐Mao Peng (Key Laboratory for the Physics and Chemistry of Nanodevices and Center for Carbon‐based Electronics Department of Electronics Peking University Beijing 100871 China) L Li Ding T Tian‐Ling Ren (School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China) Y Yeliang Wang (School of Integrated Circuits and Electronics, MIIT Key Laboratory for Low-Dimensional Quantum Structure and Devices)

Abstract

Abstract Deep learning's growing complexity demands advanced AI chips, increasing hardware costs. Time‐division multiplexing (TDM) neural networks offer a promising solution to simplify integration. However, it is difficult for current synapse transistors to physically implement TDM networks due to inherent device limitations, hindering their practical deployment in modern systems. Here, a novel graphene/2D perovskite/carbon nanotubes (CNTs) synapse transistor featuring a sandwich structure is presented. This transistor enables the realization of TDM neural networks at the hardware level. In this structure, the 2D perovskite layer, characterized by high ion concentration, serves as a neurotransmitter, thereby enhancing synaptic transmission efficiency. Additionally, the CNTs' field‐effect transistors, with their large on‐off ratio, demonstrate a wider range of synaptic current changes. The device mechanism is theoretically analyzed using molecular dynamics simulation. Furthermore, the impact of TDM on the scale, power, and latency of neural network hardware implementation is investigated. Qualitative analysis is performed to elucidate the advantages of TDM in the hardware implementation of larger deep learning models. This study offers a new approach to reducing the integration complexity of neural networks hardware implementation, holding significant promise for the development of intelligent nanoelectronic devices in the future.

Article Details

Volume / Issue Vol. 37, Issue 39
Published October 01, 2025
ISSN 0935-9648
Publisher Unknown Publisher

Journal Info

Advanced Materials

Unknown Publisher

ISSN: 0935-9648 Physical Sciences

Authors (15)

Y

Yu‐Tao Li

School of Laboratory Medicine Hubei University of Chinese Medicine Wuhan 430065 China

K

Kui Xu

Beijing Frontier Research Center for Biological Structures, State Key Laboratory of Membrane Biology, Tsinghua-Peking Joint Center for Life Sciences, School of Life Sciences, Tsinghua University

Y

Yu‐Zhe Ma

Microelectronics Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou 511453 China

J

Jun‐Ze Li

School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China

Y

Yang Luo

X

Xin‐Ru Li

School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China

P

Peng‐Hui Shen

School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China

L

Lu‐Yu Zhao

School of Integrated Circuits and Electronics MIIT Key Laboratory for Low‐Dimensional Quantum Structure and Devices Beijing Institute of Technology Beijing 100081 China

H

Hang Liu

Division of Life Science, The Hong Kong University of Science and Technology, Clear Water Bay

L

Li Ren

D

De‐Hui Li

School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan 430074 China

L

Lian‐Mao Peng

Key Laboratory for the Physics and Chemistry of Nanodevices and Center for Carbon‐based Electronics Department of Electronics Peking University Beijing 100871 China

L

Li Ding

T

Tian‐Ling Ren

School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing 100084 China

Y

Yeliang Wang

School of Integrated Circuits and Electronics, MIIT Key Laboratory for Low-Dimensional Quantum Structure and Devices