Unsupervised Adaptive Deep Learning Method For BCI Motor Imagery Decoding
This addresses the challenge of real-time, unsupervised adaptation in BCI systems for users, though it appears incremental as it builds on existing deep learning backbones.
The paper tackles the problem of adapting brain-computer interfaces for motor imagery decoding in cross-subject scenarios without supervision, achieving offline performance levels online without retraining the model.
In the context of Brain-Computer Interfaces, we propose an adaptive method that reaches 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.