lcanet++:基于横向竞争的多层神经网络鲁棒音频分类

ArXiv Pub Date : 2023-08-23 DOI:10.48550/arXiv.2308.12882
S. V. Dibbo, Juston S. Moore, Garrett T. Kenyon, M. Teti
{"title":"lcanet++:基于横向竞争的多层神经网络鲁棒音频分类","authors":"S. V. Dibbo, Juston S. Moore, Garrett T. Kenyon, M. Teti","doi":"10.48550/arXiv.2308.12882","DOIUrl":null,"url":null,"abstract":"Audio classification aims at recognizing audio signals, including speech commands or sound events. However, current audio classifiers are susceptible to perturbations and adversarial attacks. In addition, real-world audio classification tasks often suffer from limited labeled data. To help bridge these gaps, previous work developed neuro-inspired convolutional neural networks (CNNs) with sparse coding via the Locally Competitive Algorithm (LCA) in the first layer (i.e., LCANets) for computer vision. LCANets learn in a combination of supervised and unsupervised learning, reducing dependency on labeled samples. Motivated by the fact that auditory cortex is also sparse, we extend LCANets to audio recognition tasks and introduce LCANets++, which are CNNs that perform sparse coding in multiple layers via LCA. We demonstrate that LCANets++ are more robust than standard CNNs and LCANets against perturbations, e.g., background noise, as well as black-box and white-box attacks, e.g., evasion and fast gradient sign (FGSM) attacks.","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition\",\"authors\":\"S. V. Dibbo, Juston S. Moore, Garrett T. Kenyon, M. Teti\",\"doi\":\"10.48550/arXiv.2308.12882\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Audio classification aims at recognizing audio signals, including speech commands or sound events. However, current audio classifiers are susceptible to perturbations and adversarial attacks. In addition, real-world audio classification tasks often suffer from limited labeled data. To help bridge these gaps, previous work developed neuro-inspired convolutional neural networks (CNNs) with sparse coding via the Locally Competitive Algorithm (LCA) in the first layer (i.e., LCANets) for computer vision. LCANets learn in a combination of supervised and unsupervised learning, reducing dependency on labeled samples. Motivated by the fact that auditory cortex is also sparse, we extend LCANets to audio recognition tasks and introduce LCANets++, which are CNNs that perform sparse coding in multiple layers via LCA. We demonstrate that LCANets++ are more robust than standard CNNs and LCANets against perturbations, e.g., background noise, as well as black-box and white-box attacks, e.g., evasion and fast gradient sign (FGSM) attacks.\",\"PeriodicalId\":93888,\"journal\":{\"name\":\"ArXiv\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ArXiv\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2308.12882\",\"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","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2308.12882","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

音频分类的目的是识别音频信号,包括语音命令或声音事件。然而,当前的音频分类器容易受到干扰和对抗性攻击。此外,现实世界的音频分类任务经常受到有限的标记数据的影响。为了帮助弥合这些差距,之前的工作开发了神经启发的卷积神经网络(cnn),通过第一层(即LCANets)的局部竞争算法(LCA)进行稀疏编码,用于计算机视觉。lcanet结合监督学习和无监督学习进行学习,减少了对标记样本的依赖。由于听觉皮层也是稀疏的,我们将LCANets扩展到音频识别任务中,并引入了LCANets++,这是一种通过LCA在多层执行稀疏编码的cnn。我们证明了lcanet++比标准cnn和LCANets对扰动(例如背景噪声)以及黑盒和白盒攻击(例如逃避和快速梯度符号(FGSM)攻击)更具鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition
Audio classification aims at recognizing audio signals, including speech commands or sound events. However, current audio classifiers are susceptible to perturbations and adversarial attacks. In addition, real-world audio classification tasks often suffer from limited labeled data. To help bridge these gaps, previous work developed neuro-inspired convolutional neural networks (CNNs) with sparse coding via the Locally Competitive Algorithm (LCA) in the first layer (i.e., LCANets) for computer vision. LCANets learn in a combination of supervised and unsupervised learning, reducing dependency on labeled samples. Motivated by the fact that auditory cortex is also sparse, we extend LCANets to audio recognition tasks and introduce LCANets++, which are CNNs that perform sparse coding in multiple layers via LCA. We demonstrate that LCANets++ are more robust than standard CNNs and LCANets against perturbations, e.g., background noise, as well as black-box and white-box attacks, e.g., evasion and fast gradient sign (FGSM) attacks.
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
×
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