Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Interpretable deep neural networks for single-trial EEG classification

Authors
Sturm, IreneLapuschkin, SebastianSamek, WojciechMueller, Klaus-Robert
Issue Date
1-12월-2016
Publisher
ELSEVIER
Keywords
Brain-computer interfacing; Neural networks; Interpretability
Citation
JOURNAL OF NEUROSCIENCE METHODS, v.274, pp.141 - 145
Indexed
SCIE
SCOPUS
Journal Title
JOURNAL OF NEUROSCIENCE METHODS
Volume
274
Start Page
141
End Page
145
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/86577
DOI
10.1016/j.jneumeth.2016.10.008
ISSN
0165-0270
Abstract
Background: In cognitive neuroscience the potential of deep neural networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious 'black boxes' do not provide insight into neurophysiological phenomena underlying a decision. Layer wise relevance propagation (LRP) has been introduced as a novel method to explain individual network decisions. New method: We propose the application of DNNs with LRP for the first time for EEG data analysis. Through LRP the single-trial DNN decisions are transformed into heatmaps indicating each data point's relevance for the outcome of the decision. Results: DNN achieves classification accuracies comparable to those of CSP-LDA. In subjects with low performance subject-to-subject transfer of trained DNNs can improve the results. The single-trial LRP heatmaps reveal neurophysiologically plausible patterns, resembling CSP-derived scalp maps. Critically, while CSP patterns represent class-wise aggregated information, LRP heatmaps pinpoint neural patterns to single time points in single trials. Comparison with existing method(s): We compare the classification performance of DNNs to that of linear CSP-LDA on two data sets related to motor-imaginary BCI. Conclusion: We have demonstrated that DNN is a powerful non-linear tool for EEG analysis. With LRP a new quality of high-resolution assessment of neural activity can be reached. LRP is a potential remedy for the lack of interpretability of DNNs that has limited their utility in neuroscientific applications. The extreme specificity of the LRP-derived heatmaps opens up new avenues for investigating neural activity underlying complex perception or decision-related processes. (C) 2016 Elsevier B.V. All rights reserved.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE