Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Muscle anisotropy influences the phrenic nerve activation threshold in non-invasive electrical stimulation.

Medical & biological engineering & computing·2026
Same author

Charge Based Boundary Element Method with Residual Driven Adaptive Mesh Refinement for High Resolution Electrical Stimulation Modeling.

bioRxiv : the preprint server for biology·2026
Same author

Head-Specific Spatial Spectra of Electroencephalography Explained: A Sphara and BEM Investigation.

Biosensors·2025
Same author

High-Resolution EEG Source Reconstruction from PCA-Corrected BEM-FMM Reciprocal Basis Funcions: A Study with Visual Evoked Potentials from Intermittent Photic Stimulation.

bioRxiv : the preprint server for biology·2025
Same author

Impact of sensorimotor mismatch on virtual reality sickness and user experience: age-related differences in a randomized trial.

Journal of neuroengineering and rehabilitation·2025
Same author

Improved Source Localization of Auditory Evoked Fields using Reciprocal BEM-FMM.

bioRxiv : the preprint server for biology·2025

相关实验视频

Updated: Feb 26, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K

用卷积神经网络进行深度学习需要多少EEG? 预测额外数据的好处.

Marc S Seibel1,2, Jens Haueisen1,3, Thomas Jochmann1

  • 1Institute of Biomedical Engineering and Informatics, Department of Computer Science and Automation, Technische Universität Ilmenau, Ilmenau, Germany.

Journal of neural engineering
|February 25, 2026
PubMed
概括

通过神经网络准确地分类电脑电图 (EEG) 数据需要大量的数据. 使用学习曲线推断性能需要数百名受试者进行可靠的预测.

关键词:
这是分类分类的分类.数据最小化数据最小化深度学习是一种深度学习.电脑脑电图 (EEG) 是一种电脑电图.学习曲线的学习曲线.神经网络的神经网络的神经网络神经缩放规律 神经缩放规律

更多相关视频

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping
13:32

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

27.0K
Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG
12:48

Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG

Published on: June 27, 2011

18.3K

相关实验视频

Last Updated: Feb 26, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K
Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping
13:32

Recording Human Electrocorticographic ECoG Signals for Neuroscientific Research and Real-time Functional Cortical Mapping

Published on: June 26, 2012

27.0K
Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG
12:48

Investigating Social Cognition in Infants and Adults Using Dense Array Electroencephalography dEEG

Published on: June 27, 2011

18.3K

科学领域:

  • 神经科学是一个神经科学.
  • 机器学习 机器学习
  • 生物医学工程 生物医学工程

背景情况:

  • 电脑电图 (EEG) 的分类对于各种神经学应用至关重要.
  • 有限的标记数据往往限制了机器学习模型在EEG分析中的性能.
  • 了解数据要求对于高效的EEG研究设计至关重要.

研究的目的:

  • 用卷积神经网络量化训练数据大小对EEG分类准确性的影响.
  • 评估参数模型,以将神经网络性能推断到更大的EEG数据集.
  • 提供关于EEG研究数据采集策略的见解.

主要方法:

  • 在三个EEG分类任务中评估了三个神经网络架构.
  • 系统地改变了每个受试者的受试者数量和EEG数据持续时间.
  • 评估了八个参数模型,用于调整和推断学习曲线,分析预测错误和不确定性.

主要成果:

  • 学习曲线的特征 (斜率,形状,非对称性性能) 在任务之间有很大差异,但在网络架构中一致.
  • 使用缩放定律对性能进行可靠的推断,需要来自数百名受试者的数据.
  • 每个受试者增加EEG记录时间的好处在几秒钟后达到高原.

结论:

  • 特定任务的学习曲线可以指导EEG研究设计和数据采集.
  • 外推的学习曲线有助于进行成本效益分析,以获取标记的EEG数据.
  • 调查结果强调了强大的EEG分类所需的大量数据,以及延长记录时间的回报率正在下降.