基于全无机钙钛矿忆阻器的人工突触在神经形态计算中的应用

IF 9.9 2区 材料科学 Q1 Engineering
Fang Luo, Wen-Min Zhong, Xin-Gui Tang, Jia-Ying Chen, Yan-Ping Jiang, Qiu-Xiang Liu
{"title":"基于全无机钙钛矿忆阻器的人工突触在神经形态计算中的应用","authors":"Fang Luo,&nbsp;Wen-Min Zhong,&nbsp;Xin-Gui Tang,&nbsp;Jia-Ying Chen,&nbsp;Yan-Ping Jiang,&nbsp;Qiu-Xiang Liu","doi":"10.1016/j.nanoms.2023.01.003","DOIUrl":null,"url":null,"abstract":"<div><p>Artificial synapse inspired by the biological brain has great potential in the field of neuromorphic computing and artificial intelligence. The memristor is an ideal artificial synaptic device with fast operation and good tolerance. Here, we have prepared a memristor device with Au/CsPbBr<sub>3</sub>/ITO structure. The memristor device exhibits resistance switching behavior, the high and low resistance states no obvious decline after 400 switching times. The memristor device is stimulated by voltage pulses to simulate biological synaptic plasticity, such as long-term potentiation, long-term depression, pair-pulse facilitation, short-term depression, and short-term potentiation. The transformation from short-term memory to long-term memory is achieved by changing the stimulation frequency. In addition, a convolutional neural network was constructed to train/recognize MNIST handwritten data sets; a distinguished recognition accuracy of ∼96.7% on the digital image was obtained in 100 epochs, which is more accurate than other memristor-based neural networks. These results show that the memristor device based on CsPbBr<sub>3</sub> has immense potential in the neuromorphic computing system.</p></div>","PeriodicalId":33573,"journal":{"name":"Nano Materials Science","volume":"6 1","pages":"Pages 68-76"},"PeriodicalIF":9.9000,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S258996512300003X/pdfft?md5=0f4b1eada7fa50cb1b74d8992fd979b9&pid=1-s2.0-S258996512300003X-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Application of artificial synapse based on all-inorganic perovskite memristor in neuromorphic computing\",\"authors\":\"Fang Luo,&nbsp;Wen-Min Zhong,&nbsp;Xin-Gui Tang,&nbsp;Jia-Ying Chen,&nbsp;Yan-Ping Jiang,&nbsp;Qiu-Xiang Liu\",\"doi\":\"10.1016/j.nanoms.2023.01.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Artificial synapse inspired by the biological brain has great potential in the field of neuromorphic computing and artificial intelligence. The memristor is an ideal artificial synaptic device with fast operation and good tolerance. Here, we have prepared a memristor device with Au/CsPbBr<sub>3</sub>/ITO structure. The memristor device exhibits resistance switching behavior, the high and low resistance states no obvious decline after 400 switching times. The memristor device is stimulated by voltage pulses to simulate biological synaptic plasticity, such as long-term potentiation, long-term depression, pair-pulse facilitation, short-term depression, and short-term potentiation. The transformation from short-term memory to long-term memory is achieved by changing the stimulation frequency. In addition, a convolutional neural network was constructed to train/recognize MNIST handwritten data sets; a distinguished recognition accuracy of ∼96.7% on the digital image was obtained in 100 epochs, which is more accurate than other memristor-based neural networks. These results show that the memristor device based on CsPbBr<sub>3</sub> has immense potential in the neuromorphic computing system.</p></div>\",\"PeriodicalId\":33573,\"journal\":{\"name\":\"Nano Materials Science\",\"volume\":\"6 1\",\"pages\":\"Pages 68-76\"},\"PeriodicalIF\":9.9000,\"publicationDate\":\"2024-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S258996512300003X/pdfft?md5=0f4b1eada7fa50cb1b74d8992fd979b9&pid=1-s2.0-S258996512300003X-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nano Materials Science\",\"FirstCategoryId\":\"1089\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S258996512300003X\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nano Materials Science","FirstCategoryId":"1089","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S258996512300003X","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

摘要

受生物大脑启发的人工突触在神经形态计算和人工智能领域具有巨大潜力。忆阻器是一种理想的人工突触器件,具有运行速度快、耐受性好等特点。在此,我们制备了一种具有 Au/CsPbBr3/ITO 结构的忆阻器器件。该忆阻器件表现出电阻开关行为,高低电阻状态在开关 400 次后无明显下降。通过电压脉冲刺激忆阻器器件,模拟生物突触可塑性,如长期延时、长期抑制、对脉冲促进、短期抑制和短期延时。通过改变刺激频率,可实现从短期记忆到长期记忆的转变。此外,还构建了一个卷积神经网络来训练/识别MNIST手写数据集;在100个epochs中,数字图像的识别准确率达到了96.7%,比其他基于忆阻器的神经网络更准确。这些结果表明,基于铯硼铍的忆阻器在神经形态计算系统中具有巨大的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Application of artificial synapse based on all-inorganic perovskite memristor in neuromorphic computing

Artificial synapse inspired by the biological brain has great potential in the field of neuromorphic computing and artificial intelligence. The memristor is an ideal artificial synaptic device with fast operation and good tolerance. Here, we have prepared a memristor device with Au/CsPbBr3/ITO structure. The memristor device exhibits resistance switching behavior, the high and low resistance states no obvious decline after 400 switching times. The memristor device is stimulated by voltage pulses to simulate biological synaptic plasticity, such as long-term potentiation, long-term depression, pair-pulse facilitation, short-term depression, and short-term potentiation. The transformation from short-term memory to long-term memory is achieved by changing the stimulation frequency. In addition, a convolutional neural network was constructed to train/recognize MNIST handwritten data sets; a distinguished recognition accuracy of ∼96.7% on the digital image was obtained in 100 epochs, which is more accurate than other memristor-based neural networks. These results show that the memristor device based on CsPbBr3 has immense potential in the neuromorphic computing system.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Nano Materials Science
Nano Materials Science Engineering-Mechanics of Materials
CiteScore
20.90
自引率
3.00%
发文量
294
审稿时长
9 weeks
期刊介绍: Nano Materials Science (NMS) is an international and interdisciplinary, open access, scholarly journal. NMS publishes peer-reviewed original articles and reviews on nanoscale material science and nanometer devices, with topics encompassing preparation and processing; high-throughput characterization; material performance evaluation and application of material characteristics such as the microstructure and properties of one-dimensional, two-dimensional, and three-dimensional nanostructured and nanofunctional materials; design, preparation, and processing techniques; and performance evaluation technology and nanometer device applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信