提高模拟神经网络的鲁棒性:采用可解释正则化的噪声诊断方法

Alice Duque, Pedro Freire, Egor Manuylovich, Dmitrii Stoliarov, Jaroslaw Prilepsky, Sergei Turitsyn
{"title":"提高模拟神经网络的鲁棒性:采用可解释正则化的噪声诊断方法","authors":"Alice Duque, Pedro Freire, Egor Manuylovich, Dmitrii Stoliarov, Jaroslaw Prilepsky, Sergei Turitsyn","doi":"arxiv-2409.08633","DOIUrl":null,"url":null,"abstract":"This work tackles the critical challenge of mitigating \"hardware noise\" in\ndeep analog neural networks, a major obstacle in advancing analog signal\nprocessing devices. We propose a comprehensive, hardware-agnostic solution to\naddress both correlated and uncorrelated noise affecting the activation layers\nof deep neural models. The novelty of our approach lies in its ability to\ndemystify the \"black box\" nature of noise-resilient networks by revealing the\nunderlying mechanisms that reduce sensitivity to noise. In doing so, we\nintroduce a new explainable regularization framework that harnesses these\nmechanisms to significantly enhance noise robustness in deep neural\narchitectures.","PeriodicalId":501214,"journal":{"name":"arXiv - PHYS - Optics","volume":"23 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations\",\"authors\":\"Alice Duque, Pedro Freire, Egor Manuylovich, Dmitrii Stoliarov, Jaroslaw Prilepsky, Sergei Turitsyn\",\"doi\":\"arxiv-2409.08633\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work tackles the critical challenge of mitigating \\\"hardware noise\\\" in\\ndeep analog neural networks, a major obstacle in advancing analog signal\\nprocessing devices. We propose a comprehensive, hardware-agnostic solution to\\naddress both correlated and uncorrelated noise affecting the activation layers\\nof deep neural models. The novelty of our approach lies in its ability to\\ndemystify the \\\"black box\\\" nature of noise-resilient networks by revealing the\\nunderlying mechanisms that reduce sensitivity to noise. In doing so, we\\nintroduce a new explainable regularization framework that harnesses these\\nmechanisms to significantly enhance noise robustness in deep neural\\narchitectures.\",\"PeriodicalId\":501214,\"journal\":{\"name\":\"arXiv - PHYS - Optics\",\"volume\":\"23 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Optics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08633\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Optics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08633","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

这项研究解决了减轻模拟神经网络中的 "硬件噪声 "这一关键挑战,而 "硬件噪声 "是推动模拟信号处理设备发展的主要障碍。我们提出了一种全面的、与硬件无关的解决方案,以解决影响深度神经模型激活层的相关和非相关噪声。我们的方法的新颖之处在于,它能够通过揭示降低对噪声敏感性的基本机制来揭示抗噪声网络的 "黑箱 "本质。在此过程中,我们引入了一种新的可解释正则化框架,利用这些机制显著增强深度神经架构的噪声鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations
This work tackles the critical challenge of mitigating "hardware noise" in deep analog neural networks, a major obstacle in advancing analog signal processing devices. We propose a comprehensive, hardware-agnostic solution to address both correlated and uncorrelated noise affecting the activation layers of deep neural models. The novelty of our approach lies in its ability to demystify the "black box" nature of noise-resilient networks by revealing the underlying mechanisms that reduce sensitivity to noise. In doing so, we introduce a new explainable regularization framework that harnesses these mechanisms to significantly enhance noise robustness in deep neural architectures.
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
自引率
0.00%
发文量
0
期刊最新文献
Optical Label-Free Microscopy Characterization of Dielectric Nanoparticles Enwrapped Perylene Bisimide Enables Room Temperature Polariton Lasing and Photonic Lattices Chiral patterning of rough surfaces with vortex laser beams: from structured polarization to twisted forces Scaling of pseudospectra in exponentially sensitive lattices Surface Phonon Polariton Ellipsometry
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1