Neuro-GPT: Towards A Foundation Model for EEG
This work addresses data challenges in EEG-based BCI applications, but it is incremental as it adapts existing foundation model concepts to a specific domain.
The authors tackled the problem of data scarcity and heterogeneity in EEG for Brain-Computer Interface tasks by proposing Neuro-GPT, a foundation model pre-trained on large-scale EEG data, which improved classification performance in a low-data regime with 9 subjects compared to training from scratch.
To handle the scarcity and heterogeneity of electroencephalography (EEG) data for Brain-Computer Interface (BCI) tasks, and to harness the power of large publicly available data sets, we propose Neuro-GPT, a foundation model consisting of an EEG encoder and a GPT model. The foundation model is pre-trained on a large-scale data set using a self-supervised task that learns how to reconstruct masked EEG segments. We then fine-tune the model on a Motor Imagery Classification task to validate its performance in a low-data regime (9 subjects). Our experiments demonstrate that applying a foundation model can significantly improve classification performance compared to a model trained from scratch, which provides evidence for the generalizability of the foundation model and its ability to address challenges of data scarcity and heterogeneity in EEG. The code is publicly available at github.com/wenhui0206/NeuroGPT.