Hierarchical internal representation of spectral features in deep convolutional networks trained for EEG decoding

11/21/2017
by   Kay Gregor Hartmann, et al.
0

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 later 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 layer 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.

READ FULL TEXT
research
03/15/2017

Deep learning with convolutional neural networks for EEG decoding and visualization

A revised version of this article is now available at Human Brain Mappin...
research
05/11/2021

Deep Convolutional Neural Network Applied to Electroencephalography: Raw Data vs Spectral Features

The success of deep learning in computer vision has inspired the scienti...
research
12/22/2020

Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signals

While Deep Learning (DL) is often considered the state-of-the art for Ar...
research
12/20/2022

Deep Riemannian Networks for EEG Decoding

State-of-the-art performance in electroencephalography (EEG) decoding ta...
research
02/04/2020

Neural Oscillations for Encoding and Decoding Declarative Memory using EEG Signals

Declarative memory has been studied for its relationship with rememberin...
research
11/13/2020

REPAC: Reliable estimation of phase-amplitude coupling in brain networks

Recent evidence has revealed cross-frequency coupling and, particularly,...
research
01/29/2019

Minimax-optimal decoding of movement goals from local field potentials using complex spectral features

We consider the problem of predicting eye movement goals from local fiel...

Please sign up or login with your details

Forgot password? Click here to reset