Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11130%2F18%3A10392818" target="_blank" >RIV/00216208:11130/18:10392818 - isvavai.cz</a>

Alternative codes found

RIV/00064203:_____/18:10392818

Result on the web

<a href="https://doi.org/10.1109/SMC.2018.00186" target="_blank" >https://doi.org/10.1109/SMC.2018.00186</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SMC.2018.00186" target="_blank" >10.1109/SMC.2018.00186</a>

Result language

angličtina

Original language name

Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding

Original language description

When it comes to the classification of brain signals in real-life applications, the training and the prediction data are often described by different distributions. Furthermore, diverse data sets, e.g., recorded from various subjects or tasks, can even exhibit distinct feature spaces. The fact that data that have to be classified are often only available in small amounts reinforces the need for techniques to generalize learned information, as performances of brain-computer interfaces (BCIs) are enhanced by increasing quantity of available data. In this paper, we apply transfer learning to a framework based on deep convolutional neural networks (deep ConvNets) to prove the transferability of learned patterns in error-related brain signals across different tasks. The experiments described in this paper demonstrate the usefulness of transfer learning, especially improving performances when only little data can be used to distinguish between erroneous and correct realization of a task. This effect could be delimited from a transfer of merely general brain signal characteristics, underlining the transfer of error-specific information. Furthermore, we could extract similar patterns in time-frequency analyses in identical channels, leading to selective high signal correlations between the two different paradigms. Classification on the intracranial data yields in median accuracies up to (81.50 +/- 9.49) %. Decoding on only 10% of the data without pre-training reaches performances of (54.76 +/- 3.56) %, compared to (64.95 +/- 0.79) % with pre-training.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

30103 - Neurosciences (including psychophysiology)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

ISBN

978-1-5386-6650-0

ISSN

1062-922X

e-ISSN

neuvedeno

Number of pages

8

Pages from-to

1046-1053

Publisher name

IEEE

Place of publication

New York

Event location

IEEE Syst Man &amp; Cybernet Soc

Event date

Oct 7, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000459884801024