Reconfigurable Mott electronics for homogeneous neuromorphic platform  

作　　者：杨振 路英明 杨玉超 Zhen Yang;Ying-Ming Lu;Yu-Chao Yang(Beijing Advanced Innovation Center for Integrated Circuit,School of Integrated Circuits,Peking University,Beijing 100871,China;School of Electronic and Computer Engineering,Peking University,Shenzhen 518055,China;Center for Brain Inspired Chips,Institute for Artificial Intelligence,Frontiers Science Center for Nano-optoelectronics,Peking University,Beijing 100871,China;Center for Brain Inspired Intelligence,Chinese Institute for Brain Research,Beijing 102206,China)

机构地区：[1]Beijing Advanced Innovation Center for Integrated Circuit,School of Integrated Circuits,Peking University,Beijing 100871,China [2]School of Electronic and Computer Engineering,Peking University,Shenzhen 518055,China [3]Center for Brain Inspired Chips,Institute for Artificial Intelligence,Frontiers Science Center for Nano-optoelectronics,Peking University,Beijing 100871,China [4]Center for Brain Inspired Intelligence,Chinese Institute for Brain Research,Beijing 102206,China

出　　处：《Chinese Physics B》2023年第12期67-72,共6页中国物理B（英文版）

基　　金：Project supported by the National Natural Science Foundation of China (Grant Nos.61925401,92064004,61927901,and 92164302);the 111 Project (Grant No.B18001);support from the Fok Ying-Tong Education Foundation;the Tencent Foundation through the XPLORER PRIZE。

摘　　要：To simplify the fabrication process and increase the versatility of neuromorphic systems,the reconfiguration concept has attracted much attention.Here,we developed a novel electrochemical VO_(2)(EC-VO_(2))device,which can be reconfigured as synapses or LIF neurons.The ionic dynamic doping contributed to the resistance changes of VO_(2),which enables the reversible modulation of device states.The analog resistance switching and tunable LIF functions were both measured based on the same device to demonstrate the capacity of reconfiguration.Based on the reconfigurable EC-VO_(2),the simulated spiking neural network model exhibited excellent performances by using low-precision weights and tunable output neurons,whose final accuracy reached 91.92%.

关 键 词：Mott electronics RECONFIGURABLE neuromorphic computing VO_(2) 

分 类 号：TN03[电子电信—物理电子学] TP18[自动化与计算机技术—控制理论与控制工程]