A neuromorphic core based on threshold switching memristor with asynchronous address event representation circuits  

作　　者：Jinsong WEI Jilin ZHANG Xumeng ZHANG Zuheng WU Rui WANG Jian LU Tuo SHI Mansun CHAN Qi LIU Hong CHEN 

机构地区：[1]School of Microelectronics,University of Science and Technology of China,Hefei 230027,China [2]Institute of Microelectronics of Chinese Academy of Sciences,Beijing 100029,China [3]Department of Microelectronics and Nanoelectronics,Tsinghua University,Beijing 100084,China [4]Zhejiang Lab,Hangzhou 200240,China [5]Department of Electronic&Computer Engineering,The Hong Kong University of Science and Technology,Hong Kong 999077,China

出　　处：《Science China(Information Sciences)》2022年第2期207-213,共7页中国科学（信息科学）（英文版）

基　　金：supported by National key R&D Program of China(Grant No.2018AAA0103300);National Natural Science Foundation of China(Grant Nos.61751401,61804171,61825404,61732020,61674090);Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDB44000000);Major Scientific Research Project of Zhejiang Lab(Grant No.2019KC0AD02);National Science and Technology Major Project from Minister of Science and Technology,China(Grant No.2018AAA0103100);CAS-Croucher Funding(Grant Nos.CAS18EG01,172511KYSB20180135)。

摘　　要：The full memristive network hardware features high density and excellent scalability.However,recent researches on the full memristive network have been limited to a single-layer network,due to the lack of effective and flexible communication between neurons.In this design,we demonstrate a neuromorphic core based on Ag/SiO_(2)/Au threshold switching memristor,which has built-in asynchronous address event representation(AER)circuits to provide flexible communication between neurons.Since temporally sparse spikes are the medium of communication between neurons,the AER circuits are designed to transmit spikes serially which have been encoded with neurons’addresses before transmission.With the asynchronous circuits design,the AER circuits will detect neurons’output in real-time.To test the performance of the neuromorphic core,we designed a behavioral simulator for the neuromporphic core to simulate the liquid state machine(LSM)network,which achieves a 100%recognition rate in the free spoken digital dataset.The simulation results show that the neuromorphic core obtains 35 times higher performance than the CPU and111 times higher energy efficiency than the GPU.

关 键 词：leaky-integration-and-fire(LIF) MEMRISTOR threshold switching artificial neuron AER circuits asynchronous circuits on-chip communication 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN60[自动化与计算机技术—控制科学与工程]