Hierarchical processing enabled by 2D ferroelectric semiconductor transistor for low-power and high-efficiency AI vision system

Guangcheng Wu ¹Li Xiang ¹Wenqiang Wang ¹Chengdong Yao ¹Zeyi Yan ²Cheng Zhang ¹Jiaxin Wu ¹Yong Liu ¹Biyuan Zheng ¹Huawei Liu ¹Chengwei Hu ²Xingxia Sun ¹Chenguang Zhu ¹Yizhe Wang ¹Xiong Xiong ³Yanqing Wu ⁴Liang Gao ⁵Dong Li ¹Anlian Pan ¹Shengman Li¹

扫码查看

作者信息

1. Key Laboratory for Micro-Nano Physics and Technology of Hunan Province,State Key Laboratory of Chemo/Biosensing and Chemometrics,College of Materials Science and Engineering,Hunan University,Changsha 410082,China;Hunan Institute of Optoelectronic Integration,Hunan University,Changsha 410082,China
2. Hunan Institute of Advanced Sensing and Information Technology,Xiangtan University,Xiangtan 411105,China
3. School of Integrated Circuits,Peking University,Beijing 100871,China
4. Hunan Institute of Advanced Sensing and Information Technology,Xiangtan University,Xiangtan 411105,China;School of Integrated Circuits,Peking University,Beijing 100871,China
5. Wuhan National Laboratory for Optoelectronics(WNLO),Huazhong University of Science and Technology(HUST),Wuhan 430074,China
折叠

Abstract

The growth of data and Internet of Things challenges traditional hardware,which encounters efficiency and power issues owing to separate functional units for sensors,memory,and computation.In this study,we designed an α-phase indium selenide(α-In2Se3)transistor,which is a two-dimensional ferroelectric semiconductor as the channel material,to create artificial optic-neural and electro-neural synapses,enabling cutting-edge processing-in-sensor(PIS)and computing-in-memory(CIM)functionalities.As an optic-neural synapse for low-level sensory processing,the α-In2Se3 transistor exhibits a high photore-sponsivity(2855 A/W)and detectivity(2.91 x 1014 Jones),facilitating efficient feature extraction.For high-level processing tasks as an electro-neural synapse,it offers a fast program/erase speed of 40 ns/50 μs and ultralow energy consumption of 0.37 aJ/spike.An AI vision system using α-In2Se3 tran-sistors has been demonstrated.It achieved an impressive recognition accuracy of 92.63％within 12 epochs owing to the synergistic combination of the PIS and CIM functionalities.This study demonstrates the potential of the α-In2Se3 transistor in future vision hardware,enhancing processing,power efficiency,and AI applications.

Key words

Two-dimensional ferroelectric/semiconductor/Processing-in-sensor/Computing-in-memory/Synaptic device/Artificial-intelligence vision system

引用本文复制引用

基金项目

National Natural Science Foundation of China(62104066)

National Natural Science Foundation of China(52221001)

National Natural Science Foundation of China(62090035)

National Natural Science Foundation of China(U19A2090)

National Natural Science Foundation of China(U22A20138)

National Natural Science Foundation of China(52372146)

National Natural Science Foundation of China(62101181)

National Key R&D Program of China(2022YFA1402501)

National Key R&D Program of China(2022YFA1204300)

Natural Science Foundation of Hunan Province(2021JJ20016)

Science and Technology Innovation Program of Hunan Province(2021RC3061)

Key Program of Science and Technology Department of Hunan Province(2019XK2001)

Key Program of Science and Technology Department of Hunan Province(2020XK2001)

Open Project Program of Wuhan National Laboratory for Optoelectronics(2020WNLOKF016)

Open Project Program of Key Laboratory of Nanodevices and Applications,Suzhou Institute of Nano-Tech and Nano-Bionics,Chines(22ZS01)

China Postdoctoral Science Foundation(2023TQ0110)

Innovation Project of Optics Valley Laboratory(OVL2023ZD002)

出版年

2024

科学通报(英文版)

中国科学院

科学通报(英文版)

CSTPCD

ISSN：1001-6538

参考文献量60

段落导航