Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding

Kód výsledku v 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>

Nalezeny alternativní kódy

RIV/00064203:_____/18:10392818

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Cross-paradigm pretraining of convolutional networks improves intracranial EEG decoding

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

30103 - Neurosciences (including psychophysiology)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

ISBN

978-1-5386-6650-0

ISSN

1062-922X

e-ISSN

neuvedeno

Počet stran výsledku

8

Strana od-do

1046-1053

Název nakladatele

IEEE

Místo vydání

New York

Místo konání akce

IEEE Syst Man &amp; Cybernet Soc

Datum konání akce

7. 10. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000459884801024