脑电信号解码训练的深度卷积网络中频谱特征的层次内部表示

K. Hartmann, R. Schirrmeister, T. Ball
{"title":"脑电信号解码训练的深度卷积网络中频谱特征的层次内部表示","authors":"K. Hartmann, R. Schirrmeister, T. Ball","doi":"10.1109/IWW-BCI.2018.8311493","DOIUrl":null,"url":null,"abstract":"Recently, there is increasing interest and research on the interpretability of machine learning models, for example how they transform and internally represent EEG signals in Brain-Computer Interface (BCI) applications. This can help to understand the limits of the model and how it may be improved, in addition to possibly provide insight about the data itself. Schirrmeister et al. (2017) have recently reported promising results for EEG decoding with deep convolutional neural networks (ConvNets) trained in an end-to-end manner and, with a causal visualization approach, showed that they learn to use spectral amplitude changes in the input. In this study, we investigate how ConvNets represent spectral features through the sequence of intermediate stages of the network. We show higher sensitivity to EEG phase features at earlier stages and higher sensitivity to EEG amplitude features at later stages. Intriguingly, we observed a specialization of individual stages of the network to the classical EEG frequency bands alpha, beta, and high gamma. Furthermore, we find first evidence that particularly in the last convolutional layer, the network learns to detect more complex oscillatory patterns beyond spectral phase and amplitude, reminiscent of the representation of complex visual features in later layers of ConvNets in computer vision tasks. Our findings thus provide insights into how ConvNets hierarchically represent spectral EEG features in their intermediate layers and suggest that ConvNets can exploit and might help to better understand the compositional structure of EEG time series.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"446 1","pages":"1-6"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":"{\"title\":\"Hierarchical internal representation of spectral features in deep convolutional networks trained for EEG decoding\",\"authors\":\"K. Hartmann, R. Schirrmeister, T. Ball\",\"doi\":\"10.1109/IWW-BCI.2018.8311493\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, there is increasing interest and research on the interpretability of machine learning models, for example how they transform and internally represent EEG signals in Brain-Computer Interface (BCI) applications. This can help to understand the limits of the model and how it may be improved, in addition to possibly provide insight about the data itself. Schirrmeister et al. (2017) have recently reported promising results for EEG decoding with deep convolutional neural networks (ConvNets) trained in an end-to-end manner and, with a causal visualization approach, showed that they learn to use spectral amplitude changes in the input. In this study, we investigate how ConvNets represent spectral features through the sequence of intermediate stages of the network. We show higher sensitivity to EEG phase features at earlier stages and higher sensitivity to EEG amplitude features at later stages. Intriguingly, we observed a specialization of individual stages of the network to the classical EEG frequency bands alpha, beta, and high gamma. Furthermore, we find first evidence that particularly in the last convolutional layer, the network learns to detect more complex oscillatory patterns beyond spectral phase and amplitude, reminiscent of the representation of complex visual features in later layers of ConvNets in computer vision tasks. Our findings thus provide insights into how ConvNets hierarchically represent spectral EEG features in their intermediate layers and suggest that ConvNets can exploit and might help to better understand the compositional structure of EEG time series.\",\"PeriodicalId\":6537,\"journal\":{\"name\":\"2018 6th International Conference on Brain-Computer Interface (BCI)\",\"volume\":\"446 1\",\"pages\":\"1-6\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"26\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 6th International Conference on Brain-Computer Interface (BCI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IWW-BCI.2018.8311493\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 6th International Conference on Brain-Computer Interface (BCI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWW-BCI.2018.8311493","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 26

摘要

近年来,人们对机器学习模型的可解释性越来越感兴趣和研究,例如它们如何在脑机接口(BCI)应用中转换和内部表示脑电信号。这有助于了解模型的局限性以及如何改进模型,此外还可能提供有关数据本身的见解。Schirrmeister等人(2017)最近报告了用端到端方式训练的深度卷积神经网络(ConvNets)进行EEG解码的有希望的结果,并通过因果可视化方法表明,它们学会了使用输入中的频谱幅度变化。在这项研究中,我们研究了卷积神经网络如何通过网络的中间阶段序列来表示频谱特征。结果表明,早期对EEG相位特征的敏感性较高,后期对EEG振幅特征的敏感性较高。有趣的是,我们观察到网络的各个阶段专业化到经典脑电图频带α, β和高γ。此外,我们发现了第一个证据,特别是在最后一个卷积层中,网络学习检测谱相位和振幅之外的更复杂的振荡模式,这让人想起计算机视觉任务中后一层卷积网络中复杂视觉特征的表示。因此,我们的研究结果为卷积神经网络如何在中间层分层表示频谱EEG特征提供了见解,并表明卷积神经网络可以利用并可能有助于更好地理解EEG时间序列的组成结构。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Hierarchical internal representation of spectral features in deep convolutional networks trained for EEG decoding
Recently, there is increasing interest and research on the interpretability of machine learning models, for example how they transform and internally represent EEG signals in Brain-Computer Interface (BCI) applications. This can help to understand the limits of the model and how it may be improved, in addition to possibly provide insight about the data itself. Schirrmeister et al. (2017) have recently reported promising results for EEG decoding with deep convolutional neural networks (ConvNets) trained in an end-to-end manner and, with a causal visualization approach, showed that they learn to use spectral amplitude changes in the input. In this study, we investigate how ConvNets represent spectral features through the sequence of intermediate stages of the network. We show higher sensitivity to EEG phase features at earlier stages and higher sensitivity to EEG amplitude features at later stages. Intriguingly, we observed a specialization of individual stages of the network to the classical EEG frequency bands alpha, beta, and high gamma. Furthermore, we find first evidence that particularly in the last convolutional layer, the network learns to detect more complex oscillatory patterns beyond spectral phase and amplitude, reminiscent of the representation of complex visual features in later layers of ConvNets in computer vision tasks. Our findings thus provide insights into how ConvNets hierarchically represent spectral EEG features in their intermediate layers and suggest that ConvNets can exploit and might help to better understand the compositional structure of EEG time series.
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