Eng Kang Koh, Putu Andhita Dananjaya, Lingli Liu, Calvin Xiu Xian Lee, Gerard Joseph Lim, Young Seon You, Wen Siang Lew
{"title":"利用局部界面晶闸管的可调性高效处理复杂神经网络","authors":"Eng Kang Koh, Putu Andhita Dananjaya, Lingli Liu, Calvin Xiu Xian Lee, Gerard Joseph Lim, Young Seon You, Wen Siang Lew","doi":"10.1021/acsnano.4c07454","DOIUrl":null,"url":null,"abstract":"A scalable (<130 nm) resistive switching memristor that features both filamentary and interfacial switching aimed at neuromorphic computing is developed in this study. The typically perceived noise or volatility was effectively harnessed as a controlled mechanism for interfacial switching. The multilayer structure for the proposed memristor enhances switching stability by curbing ionic overmigration and mitigating leakage paths. Furthermore, the memristors showcased their reliability by demonstrating more than 15 M cycles in the filamentary mode and 1 M pulses in the interfacial mode. Additionally, retention tests at 85 °C for 10<sup>4</sup> s confirmed the stability across different states, affirming its reliability as a nonvolatile CMOS-compatible element. While many studies validate performance solely on the MNIST data set, this work also evaluates more complex data sets, demonstrating the robustness of the demonstrated memristor in supervised learning. Specifically, supervised learning simulations on MNIST and fashion MNIST data sets indicated a high learning rate with <4% deviations from numerical training, while offline inference trained on CIFAR-10 and CIFAR-100 data sets revealed <2.5% and <7% deviations caused by programing error accumulation, even with increased memristor counts for these highly complex data sets. Unsupervised learning via spike-timing-dependent plasticity further highlights the potential of the developed memristor in bridging artificial and biological paradigms, offering a significant advance toward efficient and biologically inspired computing architectures.","PeriodicalId":21,"journal":{"name":"ACS Nano","volume":null,"pages":null},"PeriodicalIF":15.8000,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Leveraging Tunability of Localized-Interfacial Memristors for Efficient Handling of Complex Neural Networks\",\"authors\":\"Eng Kang Koh, Putu Andhita Dananjaya, Lingli Liu, Calvin Xiu Xian Lee, Gerard Joseph Lim, Young Seon You, Wen Siang Lew\",\"doi\":\"10.1021/acsnano.4c07454\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A scalable (<130 nm) resistive switching memristor that features both filamentary and interfacial switching aimed at neuromorphic computing is developed in this study. The typically perceived noise or volatility was effectively harnessed as a controlled mechanism for interfacial switching. The multilayer structure for the proposed memristor enhances switching stability by curbing ionic overmigration and mitigating leakage paths. Furthermore, the memristors showcased their reliability by demonstrating more than 15 M cycles in the filamentary mode and 1 M pulses in the interfacial mode. Additionally, retention tests at 85 °C for 10<sup>4</sup> s confirmed the stability across different states, affirming its reliability as a nonvolatile CMOS-compatible element. While many studies validate performance solely on the MNIST data set, this work also evaluates more complex data sets, demonstrating the robustness of the demonstrated memristor in supervised learning. Specifically, supervised learning simulations on MNIST and fashion MNIST data sets indicated a high learning rate with <4% deviations from numerical training, while offline inference trained on CIFAR-10 and CIFAR-100 data sets revealed <2.5% and <7% deviations caused by programing error accumulation, even with increased memristor counts for these highly complex data sets. Unsupervised learning via spike-timing-dependent plasticity further highlights the potential of the developed memristor in bridging artificial and biological paradigms, offering a significant advance toward efficient and biologically inspired computing architectures.\",\"PeriodicalId\":21,\"journal\":{\"name\":\"ACS Nano\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":15.8000,\"publicationDate\":\"2024-10-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Nano\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1021/acsnano.4c07454\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Nano","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1021/acsnano.4c07454","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
Leveraging Tunability of Localized-Interfacial Memristors for Efficient Handling of Complex Neural Networks
A scalable (<130 nm) resistive switching memristor that features both filamentary and interfacial switching aimed at neuromorphic computing is developed in this study. The typically perceived noise or volatility was effectively harnessed as a controlled mechanism for interfacial switching. The multilayer structure for the proposed memristor enhances switching stability by curbing ionic overmigration and mitigating leakage paths. Furthermore, the memristors showcased their reliability by demonstrating more than 15 M cycles in the filamentary mode and 1 M pulses in the interfacial mode. Additionally, retention tests at 85 °C for 104 s confirmed the stability across different states, affirming its reliability as a nonvolatile CMOS-compatible element. While many studies validate performance solely on the MNIST data set, this work also evaluates more complex data sets, demonstrating the robustness of the demonstrated memristor in supervised learning. Specifically, supervised learning simulations on MNIST and fashion MNIST data sets indicated a high learning rate with <4% deviations from numerical training, while offline inference trained on CIFAR-10 and CIFAR-100 data sets revealed <2.5% and <7% deviations caused by programing error accumulation, even with increased memristor counts for these highly complex data sets. Unsupervised learning via spike-timing-dependent plasticity further highlights the potential of the developed memristor in bridging artificial and biological paradigms, offering a significant advance toward efficient and biologically inspired computing architectures.
期刊介绍:
ACS Nano, published monthly, serves as an international forum for comprehensive articles on nanoscience and nanotechnology research at the intersections of chemistry, biology, materials science, physics, and engineering. The journal fosters communication among scientists in these communities, facilitating collaboration, new research opportunities, and advancements through discoveries. ACS Nano covers synthesis, assembly, characterization, theory, and simulation of nanostructures, nanobiotechnology, nanofabrication, methods and tools for nanoscience and nanotechnology, and self- and directed-assembly. Alongside original research articles, it offers thorough reviews, perspectives on cutting-edge research, and discussions envisioning the future of nanoscience and nanotechnology.