Deep Learning With Convolutional Neural Networks for EEG Decoding and Visualization
Deep Learning With Convolutional Neural Networks for EEG Decoding and Visualization
复制标题
DOI：
10.1002/hbm.23730
复制
发表时间：
2017-11-01
影响因子：
4.8
通讯作者：
Ball, Tonio
中科院分区：
文献类型：
--
作者：
Schirrmeister, Robin Tibor;Springenberg, Jost Tobias;Ball, Tonio
使用卷积神经网络的深度学习（深度ConvNets）通过端到端学习（即从原始数据中学习）彻底改变了计算机视觉。人们对使用深度ConvNets进行端到端EEG分析的兴趣越来越大，但仍然需要更好地了解如何设计和训练ConvNets进行端到端EEG解码，以及如何可视化ConvNets学习的信息EEG特征。在这里，我们研究了具有一系列不同架构的深度ConvNets，旨在从原始EEG中解码想象或执行的任务。我们的研究结果表明，机器学习领域的最新进展，包括批量归一化和指数线性单元，以及裁剪训练策略，提高了深度ConvNets解码性能，至少达到了与广泛使用的滤波器组公共空间模式（FBCSP）算法一样好的性能（平均解码精度82.1%FBCSP，84.0%深度ConvNets）。虽然FBCSP被设计为使用频谱功率调制，但ConvNets使用的功能并不是先验固定的。我们用于可视化学习特征的新方法表明，ConvNets确实学会了在alpha，beta和高伽马频率中使用频谱功率调制，并且通过揭示不同频带中特征对解码决策的因果贡献的拓扑结构，证明了对空间映射学习特征是有用的。因此，我们的研究展示了如何设计和训练ConvNets来解码来自原始EEG的任务相关信息，而无需手工制作的功能，并强调了深度ConvNets与先进的可视化技术相结合的潜力，用于基于EEG的大脑映射。(C)2017 Wiley Periodicals，Inc.
Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. (C) 2017 Wiley Periodicals, Inc.