A Strong and Simple Deep Learning Baseline for BCI MI Decoding

TL;DR

This paper introduces EEG-SimpleConv, a simple yet effective 1D CNN baseline for Motor Imagery decoding in BCI, demonstrating competitive performance and efficiency across multiple datasets.

Contribution

The paper presents a straightforward 1D CNN baseline for BCI MI decoding that uses standard components, promoting ease of adoption and strong cross-subject transfer.

Findings

EEG-SimpleConv performs as well or better than recent approaches.

It offers high efficiency with low inference time.

It demonstrates strong knowledge transfer across subjects.

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.