A Strong and Simple Deep Learning Baseline for BCI MI Decoding

Yassine El Ouahidi, Vincent Gripon, Bastien Pasdeloup, Ghaith Bouallegue, Nicolas Farrugia +1 more
9/11/2023
eess.SPcs.LGq-bio.NC

Official code: elouayas/EEGSimpleConv (52 stars, last commit 2025-08-20).

Abstract

We propose EEG-SimpleConv, a straightforward 1D convolutional neural network for Motor Imagery decoding in BCI. Our main motivation is to propose a simple and performing baseline to compare to, using only very standard ingredients from the literature. We evaluate its performance on four EEG Motor Imagery datasets, including simulated online setups, and compare it to recent Deep Learning and Machine Learning approaches. EEG-SimpleConv is at least as good or far more efficient than other approaches, showing strong knowledge-transfer capabilities across subjects, at the cost of a low inference time. We advocate that using off-the-shelf ingredients rather than coming with ad-hoc solutions can significantly help the adoption of Deep Learning approaches for BCI. We make the code of the models and the experiments accessible.

View on arXivView PDF

Code Implementations(1)

elouayas/EEGSimpleConvOfficial

Repository of EEG-Simpleconv original paper

526Python, Jupyter NotebookSep 5, 20231 years ago

Similar Papers

Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding

90% match2024

Geometric Neural Network based on Phase Space for BCI-EEG decoding

88% match1 repo52024

EEGEncoder: Advancing BCI with Transformer-Based Motor Imagery Classification

86% match2024

Decoding Motor Behavior Using Deep Learning and Reservoir Computing

85% match1 repo2025

Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning

85% match2025

Deep Learning Architectures for Code-Modulated Visual Evoked Potentials Detection

84% match2025

Cite this paper

@article{ouahidi2023strong,
  title  = {A Strong and Simple Deep Learning Baseline for BCI MI Decoding},
  author = {Yassine El Ouahidi and Vincent Gripon and Bastien Pasdeloup and Ghaith Bouallegue and Nicolas Farrugia and Giulia Lioi},
  year   = {2023},
  eprint = {2309.07159},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.07159v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.07159.svg)](https://codeofpaper.com/paper/2309.07159)

Discussion