Blame for README.md

---
library_name: braindecode
license: mit
pipeline_tag: feature-extraction
base_model: braindecode/STEEGFormer-small
tags:
- braindecode
- CORTEG
- ieeg
- ecog
- foundation-model
- pytorch_model_hub_mixin
datasets:
- nm000245
- nm000172
- nm000139
- nm000135
- Kaya2018
- Won2022
- nm000129
- nm000339
- SparrKULee
- SEED-V

---

# CORTEG, ST-EEGFormer small backbone

The starting point of CORTEG ([Yang et al., 2026](https://arxiv.org/abs/2605.10337)),
ST-EEGFormer small adapted to intracranial recordings, for
[`braindecode.models.CORTEG`](https://braindecode.org/stable/generated/braindecode.models.CORTEG.html):
the ST-EEGFormer small encoder ([`checkpoint-300.pth`](https://github.com/LiuyinYang1101/STEEGFormer/releases/download/ST-EEGFormer-small/checkpoint-300.pth),
sha256 `98d2848abdaea7a143d399c07f67f8782e07dd66e7c309ddb058c7158a8a8b02`, through its conversion
[braindecode/STEEGFormer-small](https://huggingface.co/braindecode/STEEGFormer-small) at revision
`633c9c0d`), 25.3M parameters. The
high-gamma patch embedding, which the scalp model does not have, is warm-started
from the low-frequency one, linearly interpolated from 16 to 25 samples, as the
authors' `build_model` does ([LiuyinYang1101/CORTEG](https://github.com/LiuyinYang1101/CORTEG/tree/caafb78fbebdd9448814f96d7e61083a3eb62663),
`experiments/run_regression_hilo_clean.py`); it matches theirs to
0.0e+00 in float32 on CPU. `convert_corteg_checkpoint.py` in this
repository reproduces the conversion.


<!-- braindecode:training-data -->
## Training data

The data that shaped these weights. The ids are the `datasets:` field of this card,
which braindecode reads into `model.card_data.datasets` when you call
`from_pretrained` (MOABB class names for MOABB datasets, OpenNeuro / NEMAR
accessions, Hub ids otherwise). `nm`/`on` ids are datasets on [NEMAR](https://nemar.org)
(`on` = NEMAR's copy of the OpenNeuro dataset with the same number). Rows marked
`private:` are data the authors did not release; they are not in `datasets:`.

| `datasets:` id | Dataset | Stage | Modality |
|---|---|---|---|
| [`nm000245`](https://nemar.org/dataset/nm000245) | [EEG-MI-BCI: Cho et al. 2017, EEG datasets for motor imagery BCI (52 subjects, 64 ch, left/right-hand MI; GigaDB 100295); MOABB Cho2017](http://gigadb.org/dataset/100295) | pretraining | EEG |
| [`nm000172`](https://nemar.org/dataset/nm000172) | [High Gamma Dataset (HGD), Schirrmeister et al. 2017 (20 subjects, 128 ch, executed movements); MOABB Schirrmeister2017](https://gin.g-node.org/robintibor/high-gamma-dataset) | pretraining | EEG |
| [`nm000139`](https://nemar.org/dataset/nm000139) | [BCI Competition IV dataset 2a (9 subjects, 22 ch, 4-class MI); MOABB BNCI2014_001](https://www.bbci.de/competition/iv/#dataset2a) | pretraining | EEG |
| [`nm000135`](https://nemar.org/dataset/nm000135) | [BCI Competition IV dataset 2b (9 subjects, 3 ch, 2-class MI); MOABB BNCI2014_004](https://www.bbci.de/competition/iv/#dataset2b) | pretraining | EEG |
| `Kaya2018` | [Kaya et al. 2018, A large electroencephalographic motor imagery dataset for EEG BCIs (Sci. Data 5:180211; Figshare collection 3917698). Paper uses two subsets, 'Large-MI-Classic' and 'Large-MI-5F'. MOABB Kaya2018 (moabb>=1.7.2) loads only the 17 CLA files, not the 5F (or HaLT) files](https://figshare.com/collections/A_large_electroencephalographic_motor_imagery_dataset_for_electroencephalographic_brain_computer_interfaces/3917698) (NEMAR [nm000137](https://nemar.org/dataset/nm000137) holds a subset of it) | pretraining | EEG |
| `Won2022` | [Won et al. 2022, EEG dataset for RSVP and P300 speller BCIs (Sci. Data 9:388; 55 participants P300 speller, 50 RSVP; Figshare collection 5769449); not in MOABB](https://doi.org/10.6084/m9.figshare.c.5769449.v1) | pretraining | EEG |
| [`nm000129`](https://nemar.org/dataset/nm000129) | [BETA: large benchmark database toward SSVEP-BCI application, Liu et al. 2020 (70 subjects, 40 targets); MOABB Liu2020BETA](https://doi.org/10.3389/fnins.2020.00627) | pretraining | EEG |
| [`nm000339`](https://nemar.org/dataset/nm000339) | [Stieger et al. 2021, continuous sensorimotor-rhythm BCI learning in a large population (62 subjects, ~600 h, 62 ch; Figshare 13123148); MOABB Stieger2021](https://doi.org/10.6084/m9.figshare.13123148.v1) | pretraining | EEG |
| `SparrKULee` | [SparrKULee: speech-evoked auditory response repository of KU Leuven (Bollens et al. 2023; 85 participants, 64 ch BioSemi); called 'KUL Auditory Decoding Dataset' in the paper](https://doi.org/10.48804/K3VSND) (NEMAR [nm000238](https://nemar.org/dataset/nm000238) holds a subset of it) | pretraining | EEG |
| `SEED-V` | [SEED-V emotion EEG dataset (Liu et al. 2022; 16 subjects x 3 sessions, 62 ch, five emotions)](https://bcmi.sjtu.edu.cn/home/seed/seed-v.html) | pretraining | EEG |
| `private:KU-Leuven-in-house-EEG` | In-house EEG recorded in the authors' lab (KU Leuven Laboratory for Neuro- & Psychophysiology), multiple paradigms (e.g. MI and SSVEP) and diverse montages; not released, not itemised | pretraining | EEG |

- MAE self-supervised pre-training, 300 epochs (release note). MAE pre-training corpus of App. E.2 (pp. 25-26), '11 public datasets' + an in-house set, as the paper lists them: 1) EEG-MI-BCI (Cho et al., 2017) -> Cho2017; 2) HGD (Schirrmeister et al., 2017) -> Schirrmeister2017; 3) BCI-Comp-IV2a (Tangermann et al., 2012) -> BNCI2014_001 (official training session only; the official test session was the validation split, E.4 p.26); 4) BCI-Comp-IV2b (Tangermann et al., 2012) -> BNCI2014_004; 5) Large-MI-Classic and 6) Large-MI-5F (both Kaya et al., 2018) -> Kaya2018 (one dataset, two paradigm subsets); 7) P300 (Won et al., 2022: P300 speller + RSVP) -> Won2022; 8) SSVEP (Liu et al., 2020 = BETA) -> Liu2020BETA; 9) Online MI BCI Classification (Stieger et al., 2021) -> Stieger2021; 10) KUL Auditory Decoding Dataset (Bollens et al., 2023 = SparrKULee) -> SparrKULee; 11) SEED-V (Liu et al., 2022) -> SEED-V; plus in-house EEG recorded in the authors' lab (multiple paradigms, e.g. MI and SSVEP) -> private:KU-Leuven-in-house-EEG. Preprocessing: notch, 0.1-64 Hz band-pass, 128 Hz, per-channel z-score (E.3). Windows: 6 s / 0.5 s hop for continuous sets, 6 s / 2.5 s hop for the three large MI sets, 2 s / 0.125 s hop for SSVEP (E.4). Validation: BCI-Comp-IV2a official test set; 20% held out for every other set; >8M overlapping segments overall.
- Sources: Yang et al., ICLR 2026, https://openreview.net/forum?id=5Xwm8e6vbh; PDF via Wayback snapshot http://web.archive.org/web/20260609032700/https://openreview.net/pdf?id=5Xwm8e6vbh App. E.2, p.25; https://github.com/LiuyinYang1101/STEEGFormer/releases/tag/ST-EEGFormer-small (release body).

### Scope of this warm-start

This checkpoint inherits the scalp-EEG MAE corpus above from `braindecode/STEEGFormer-small`. No Stanford iEEG training has occurred here. The high-gamma patch embedding is warm-started from the low-frequency embedding; the spatial adapter and task readout are initialized on load and require downstream training.


## Usage

```python
from braindecode.models import CORTEG

model = CORTEG.from_pretrained(
    "braindecode/corteg-small-pretrained", n_outputs=5, n_times=128, chs_info=raw.info["chs"]
)
```

The spatial adapter, the head and, with `merge_strategy="layerwise_gate"`, the
gate are not in these files: Braindecode initializes them on load, the adapter
from the electrode positions of `chs_info` (metres). The paper then trains the
adapter, the high-gamma embedding, LoRA (r=4, alpha=16) on the last four blocks
with their LayerNorms, and the head, with the rest frozen. See
[`braindecode/corteg-stanford-pooled`](https://huggingface.co/braindecode/corteg-stanford-pooled)
for the authors' trained Stanford model and the input streams.

## Limitations

These files hold no trained intracranial component, so the model needs
training before prediction. The check above covers the float32 CPU tensors of
the warm start.

## Citation

```bibtex
@inproceedings{yang2026corteg,
  title     = {{CORTEG}: Foundation Models Enable Cross-Modality Representation Transfer
               from Scalp to Intracranial Brain Recordings},
  author    = {Yang, Liuyin and Sun, Qiang and Van Dyck, Bob and Calvo Merino, Eva and
               Van Hulle, Marc M.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}
```

## License

The ST-EEGFormer weights are released by Liuyin Yang under the MIT licence
(`LICENSE`). Braindecode's code is BSD-3-Clause.


## Cite Braindecode

If you use this braindecode port in scientific work, cite the software on Zenodo,
[doi:10.5281/zenodo.17699192](https://doi.org/10.5281/zenodo.17699192),
and the original model and datasets cited above.

```bibtex
@software{braindecode,
  author = {Aristimunha, Bruno and
            Guetschel, Pierre and
            Wimpff, Martin and
            Gemein, Lukas and
            Rommel, Cedric and
            Banville, Hubert and
            Sliwowski, Maciej and
            Wilson, Daniel and
            Brandt, Simon and
            Gnassounou, Théo and
            Paillard, Joseph and
            {Junqueira Lopes}, Bruna and
            Sedlar, Sara and
            Moreau, Thomas and
            Chevallier, Sylvain and
            Gramfort, Alexandre and
            Schirrmeister, Robin Tibor},
  title = {Braindecode: toolbox for decoding raw electrophysiological brain data
           with deep learning models},
  url = {https://github.com/braindecode/braindecode},
  doi = {10.5281/zenodo.17699192},
  publisher = {Zenodo},
  license = {BSD-3-Clause},
}
```