Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Self-supervised representation learning from electroencephalography signals

Abstract: 

The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create learning problems that can be solved with standard supervised approaches, has shown great promise as a pretraining or feature learning approach in fields like computer vision and time series processing. In this work, we present self-supervision strategies that can be used to learn informative representations from multivariate time series. One successful approach relies on predicting whether time windows are sampled from the same temporal context or not. As demonstrated on a clinically relevant task (sleep scoring) and with two electroencephalography datasets, our approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels.

up
0 users have voted:

Paper Details

Authors:
Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort
Submitted On:
13 October 2019 - 8:58pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Hubert Banville
Paper Code:
129
Document Year:
2019
Cite

Document Files

mlsp2019_poster_hjb_final.pdf

(34)

Subscribe

[1] Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort, "Self-supervised representation learning from electroencephalography signals", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4866. Accessed: Nov. 14, 2019.
@article{4866-19,
url = {http://sigport.org/4866},
author = {Hubert Banville; Isabela Albuquerque; Aapo Hyvärinen; Graeme Moffat; Denis-Alexander Engemann; Alexandre Gramfort },
publisher = {IEEE SigPort},
title = {Self-supervised representation learning from electroencephalography signals},
year = {2019} }
TY - EJOUR
T1 - Self-supervised representation learning from electroencephalography signals
AU - Hubert Banville; Isabela Albuquerque; Aapo Hyvärinen; Graeme Moffat; Denis-Alexander Engemann; Alexandre Gramfort
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4866
ER -
Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort. (2019). Self-supervised representation learning from electroencephalography signals. IEEE SigPort. http://sigport.org/4866
Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort, 2019. Self-supervised representation learning from electroencephalography signals. Available at: http://sigport.org/4866.
Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort. (2019). "Self-supervised representation learning from electroencephalography signals." Web.
1. Hubert Banville, Isabela Albuquerque, Aapo Hyvärinen, Graeme Moffat, Denis-Alexander Engemann, Alexandre Gramfort. Self-supervised representation learning from electroencephalography signals [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4866