Deep learning with convolutional neural networks for EEG decoding and visualization

Abstract

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. Hum Brain Mapp 38:5391–5420, 2017 . © 2017 Wiley Periodicals, Inc.

Cited by papers we hold 10

• EEG-based brain-computer interface enables real-time robotic hand control at individual finger level · 2025
  Not checked
• Mind the gap: State-of-the-art technologies and applications for EEG-based brain–computer interfaces · 2021
  Not checked
• Editorial: Recent Developments of Deep Learning in Analyzing, Decoding, and Understanding Neuroimaging Signals · 2021
  Not checked
• Brain–computer interface robotics for hand rehabilitation after stroke: a systematic review · 2021
  No notice
• A Novel Multimodal Approach for Hybrid Brain–Computer Interface · 2020
  Not checked
• Decoding P300 Variability Using Convolutional Neural Networks · 2019
  Not checked
• A Parallel Multiscale Filter Bank Convolutional Neural Networks for Motor Imagery EEG Classification · 2019
  Not checked
• Neural Speech Tracking in the Theta and in the Delta Frequency Band Differentially Encode Clarity and Comprehension of Speech in Noise · 2019
  No notice
• EEG-Based Brain-Computer Interfaces Using Motor-Imagery: Techniques and Challenges · 2019
  No notice
• Characterizing Focused Attention and Working Memory Using EEG · 2018
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.