Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2506.09110 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913111541284864 |
|---|---|
| author | Ma, Jingying Wu, Feng Lin, Qika Xing, Yucheng Liu, Chenyu Jia, Ziyu Feng, Mengling |
| author_facet | Ma, Jingying Wu, Feng Lin, Qika Xing, Yucheng Liu, Chenyu Jia, Ziyu Feng, Mengling |
| contents | Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models, current approaches still yield clinically uninterpretable and weakly discriminative representations, inefficiently capturing global dependencies and neglecting important local neural events. We present CodeBrain, a two-stage EFM designed to fill this gap. In the first stage, we introduce the TFDual-Tokenizer, which decouples heterogeneous temporal and frequency EEG signals into discrete tokens, quadratically expanding the representation space to enhance discriminative power and offering domain-specific representation-level interpretability by suggesting potential links to neural events and spectral rhythms. In the second stage, we propose the multi-scale EEGSSM architecture, which combines structured global convolution with sliding window attention to efficiently capture both sparse long-range and local dependencies, reflecting the brain's small-world topology. Pretrained on the largest public EEG corpus, CodeBrain achieves strong generalization across eight downstream tasks and ten datasets under distribution shifts, supported by comprehensive ablations, scaling-law analyzes, and interpretability evaluations. The code and the pretrained weights are available at https://github.com/jingyingma01/CodeBrain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09110 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model Ma, Jingying Wu, Feng Lin, Qika Xing, Yucheng Liu, Chenyu Jia, Ziyu Feng, Mengling Machine Learning Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models, current approaches still yield clinically uninterpretable and weakly discriminative representations, inefficiently capturing global dependencies and neglecting important local neural events. We present CodeBrain, a two-stage EFM designed to fill this gap. In the first stage, we introduce the TFDual-Tokenizer, which decouples heterogeneous temporal and frequency EEG signals into discrete tokens, quadratically expanding the representation space to enhance discriminative power and offering domain-specific representation-level interpretability by suggesting potential links to neural events and spectral rhythms. In the second stage, we propose the multi-scale EEGSSM architecture, which combines structured global convolution with sliding window attention to efficiently capture both sparse long-range and local dependencies, reflecting the brain's small-world topology. Pretrained on the largest public EEG corpus, CodeBrain achieves strong generalization across eight downstream tasks and ten datasets under distribution shifts, supported by comprehensive ablations, scaling-law analyzes, and interpretability evaluations. The code and the pretrained weights are available at https://github.com/jingyingma01/CodeBrain. |
| title | CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.09110 |