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.
@article{arxiv.2311.03764,
title = {Neuro-GPT: Towards A Foundation Model for EEG},
author = {Wenhui Cui and Woojae Jeong and Philipp Thölke and Takfarinas Medani and Karim Jerbi and Anand A. Joshi and Richard M. Leahy},
journal= {arXiv preprint arXiv:2311.03764},
year = {2024}
}
Comments
Paper accepted by the 2024 IEEE International Symposium on Biomedical Imaging (ISBI)