Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding - Equipe Better Representations for Artificial Intelligence
Communication Dans Un Congrès Année : 2024

Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding

Résumé

In the context of Brain-Computer Interfaces, we propose an adaptive method that reach offline performance level while being usable online without requiring supervision. Interestingly, our method does not require retraining the model, as it consists in using a frozen efficient deep learning backbone while continuously realigning data, both at input and latent spaces, based on streaming observations. We demonstrate its efficiency for Motor Imagery brain decoding from electroencephalography data, considering challenging cross-subject scenarios. For reproducibility, we share the code of our experiments.
Fichier principal
Vignette du fichier
Ouahidi et al. - Unsupervised Adaptive Deep Learning Method For BCI.pdf (218.37 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04645175 , version 1 (11-07-2024)

Identifiants

  • HAL Id : hal-04645175 , version 1

Citer

Yassine El Ouahidi, Giulia Lioi, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon. Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding. European Signal Processing Conference (EUSIPCO), Aug 2024, Lyon, France. ⟨hal-04645175⟩
34 Consultations
28 Téléchargements

Partager

More