---
license: bsd-3-clause
library_name: braindecode
pipeline_tag: feature-extraction
tags:
  - eeg
  - biosignal
  - pytorch
  - neuroscience
  - braindecode
  - convolutional
---

# SincShallowNet

Sinc-ShallowNet from Borra, D et al (2020) [borra2020].

> **Architecture-only repository.** Documents the
> `braindecode.models.SincShallowNet` class. **No pretrained weights are
> distributed here.** Instantiate the model and train it on your own
> data.

## Quick start

```bash
pip install braindecode
```

```python
from braindecode.models import SincShallowNet

model = SincShallowNet(
    n_chans=22,
    sfreq=250,
    input_window_seconds=4.0,
    n_outputs=4,
)
```

The signal-shape arguments above are illustrative defaults — adjust to
match your recording.

## Documentation
- Full API reference: <https://braindecode.org/stable/generated/braindecode.models.SincShallowNet.html>
- Interactive browser (live instantiation, parameter counts):
  <https://huggingface.co/spaces/braindecode/model-explorer>
- Source on GitHub: <https://github.com/braindecode/braindecode/blob/master/braindecode/models/sinc_shallow.py#L11>


## Architecture

![SincShallowNet architecture](https://ars.els-cdn.com/content/image/1-s2.0-S0893608020302021-gr2_lrg.jpg)


## Parameters

| Parameter | Type | Description |
|---|---|---|
| `num_time_filters` | int | Number of temporal filters in the SincFilter layer. |
| `time_filter_len` | int | Size of the temporal filters. |
| `depth_multiplier` | int | Depth multiplier for spatial filtering. |
| `activation` | nn.Module, optional | Activation function to use. Default is nn.ELU(). |
| `drop_prob` | float, optional | Dropout probability. Default is 0.5. |
| `first_freq` | float, optional | The starting frequency for the first Sinc filter. Default is 5.0. |
| `min_freq` | float, optional | Minimum frequency allowed for the low frequencies of the filters. Default is 1.0. |
| `freq_stride` | float, optional | Frequency stride for the Sinc filters. Controls the spacing between the filter frequencies. Default is 1.0. |
| `padding` | str, optional | Padding mode for convolution, either 'same' or 'valid'. Default is 'same'. |
| `bandwidth` | float, optional | Initial bandwidth for each Sinc filter. Default is 4.0. |
| `pool_size` | int, optional | Size of the pooling window for the average pooling layer. Default is 55. |
| `pool_stride` | int, optional | Stride of the pooling operation. Default is 12. |


## References

1. Borra, D., Fantozzi, S., & Magosso, E. (2020). Interpretable and lightweight convolutional neural network for EEG decoding: Application to movement execution and imagination. Neural Networks, 129, 55-74.
2. Sinc-ShallowNet re-implementation source code: https://github.com/marcellosicbaldi/SincNet-Tensorflow


## Citation

Cite the original architecture paper (see *References* above) and braindecode:

```bibtex
@article{aristimunha2025braindecode,
  title   = {Braindecode: a deep learning library for raw electrophysiological data},
  author  = {Aristimunha, Bruno and others},
  journal = {Zenodo},
  year    = {2025},
  doi     = {10.5281/zenodo.17699192},
}
```

## License

BSD-3-Clause for the model code (matching braindecode).
Pretraining-derived weights, if you fine-tune from a checkpoint,
inherit the licence of that checkpoint and its training corpus.