Harnessing adaptive dynamics in neuro-memristive nanowire networks for transfer learning

Ruomin Zhu, Joel Hochstetter, Alon Loeffler, A. Diaz-Alvarez, A. Stieg, J. Gimzewski, T. Nakayama, Z. Kuncic
{"title":"Harnessing adaptive dynamics in neuro-memristive nanowire networks for transfer learning","authors":"Ruomin Zhu, Joel Hochstetter, Alon Loeffler, A. Diaz-Alvarez, A. Stieg, J. Gimzewski, T. Nakayama, Z. Kuncic","doi":"10.1109/ICRC2020.2020.00007","DOIUrl":null,"url":null,"abstract":"Nanowire networks (NWNs) represent a unique hardware platform for neuromorphic information processing. In addition to exhibiting synapse-like resistive switching memory at their cross-point junctions, their self-assembly confers a neural network-like topology to their electrical circuitry, something that is impossible to achieve through conventional top-down fabrication approaches. In addition to their low power requirements, cost effectiveness and efficient interconnects, neuromorphic NWNs are also fault-tolerant and self-healing. These highly attractive properties can be largely attributed to their complex network connectivity, which enables a rich repertoire of adaptive nonlinear dynamics, including edge-of-chaos criticality. Here, we show how the adaptive dynamics intrinsic to neuromorphic NWNs can be harnessed to achieve transfer learning. We demonstrate this through simulations of a reservoir computing implementation in which NWNs perform the well-known benchmarking task of Mackey-Glass (MG) signal forecasting. First we show how NWNs can predict MG signals with arbitrary degrees of unpredictability (i.e. chaos). We then show that NWNs pre-exposed to a MG signal perform better in forecasting than NWNs without prior experience of an MG signal. This type of transfer learning is enabled by the network’s collective memory of previous states. Overall, their adaptive signal processing capabilities make neuromorphic NWNs promising candidates for emerging real-time applications in IoT devices in particular, at the far edge.","PeriodicalId":320580,"journal":{"name":"2020 International Conference on Rebooting Computing (ICRC)","volume":"129 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Rebooting Computing (ICRC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRC2020.2020.00007","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

Abstract

Nanowire networks (NWNs) represent a unique hardware platform for neuromorphic information processing. In addition to exhibiting synapse-like resistive switching memory at their cross-point junctions, their self-assembly confers a neural network-like topology to their electrical circuitry, something that is impossible to achieve through conventional top-down fabrication approaches. In addition to their low power requirements, cost effectiveness and efficient interconnects, neuromorphic NWNs are also fault-tolerant and self-healing. These highly attractive properties can be largely attributed to their complex network connectivity, which enables a rich repertoire of adaptive nonlinear dynamics, including edge-of-chaos criticality. Here, we show how the adaptive dynamics intrinsic to neuromorphic NWNs can be harnessed to achieve transfer learning. We demonstrate this through simulations of a reservoir computing implementation in which NWNs perform the well-known benchmarking task of Mackey-Glass (MG) signal forecasting. First we show how NWNs can predict MG signals with arbitrary degrees of unpredictability (i.e. chaos). We then show that NWNs pre-exposed to a MG signal perform better in forecasting than NWNs without prior experience of an MG signal. This type of transfer learning is enabled by the network’s collective memory of previous states. Overall, their adaptive signal processing capabilities make neuromorphic NWNs promising candidates for emerging real-time applications in IoT devices in particular, at the far edge.
利用神经记忆纳米线网络中的自适应动力学进行迁移学习
纳米线网络为神经形态信息处理提供了一种独特的硬件平台。除了在交叉点处表现出类似突触的电阻开关记忆外,它们的自组装还赋予了电路类似神经网络的拓扑结构,这是通过传统的自上而下的制造方法无法实现的。除了低功耗要求、成本效益和高效互连外,神经形态NWNs还具有容错和自我修复能力。这些极具吸引力的特性在很大程度上归功于它们复杂的网络连接,这使得自适应非线性动力学具有丰富的功能,包括混沌边缘临界性。在这里,我们展示了如何利用神经形态NWNs固有的自适应动力学来实现迁移学习。我们通过油藏计算实现的模拟来证明这一点,其中NWNs执行著名的Mackey-Glass (MG)信号预测的基准任务。首先,我们展示了NWNs如何预测具有任意程度不可预测性(即混沌)的MG信号。然后我们表明,与没有MG信号经验的NWNs相比,预先暴露于MG信号的NWNs在预测方面表现更好。这种类型的迁移学习是由网络对以前状态的集体记忆实现的。总的来说,它们的自适应信号处理能力使神经形态NWNs成为物联网设备中新兴实时应用的有希望的候选者,特别是在远端。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信