README.md

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

# FBLightConvNet

LightConvNet from Ma, X et al (2023) [lightconvnet].

> **Architecture-only repository.** Documents the
> `braindecode.models.FBLightConvNet` 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 FBLightConvNet

model = FBLightConvNet(
    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.FBLightConvNet.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/fblightconvnet.py#L18>


## Architecture

![FBLightConvNet architecture](https://raw.githubusercontent.com/Ma-Xinzhi/LightConvNet/refs/heads/main/network_architecture.png)


## Parameters

| Parameter | Type | Description |
|---|---|---|
| `n_bands` | int or None or list of tuple of int, default=8 | Number of frequency bands or a list of frequency band tuples. If a list of tuples is provided, each tuple defines the lower and upper bounds of a frequency band. |
| `n_filters_spat` | int, default=32 | Number of spatial filters in the depthwise convolutional layer. |
| `n_dim` | int, default=3 | Number of dimensions for the temporal reduction layer. |
| `stride_factor` | int, default=4 | Stride factor used for reshaping the temporal dimension. |
| `activation` | nn.Module, default=nn.ELU | Activation function class to apply after convolutional layers. |
| `verbose` | bool, default=False | If True, enables verbose output during filter creation using mne. |
| `filter_parameters` | dict, default={} | Additional parameters for the FilterBankLayer. |
| `heads` | int, default=8 | Number of attention heads in the multi-head attention mechanism. |
| `weight_softmax` | bool, default=True | If True, applies softmax to the attention weights. |
| `bias` | bool, default=False | If True, includes a bias term in the convolutional layers. |


## References

1. Ma, X., Chen, W., Pei, Z., Liu, J., Huang, B., & Chen, J. (2023). A temporal dependency learning CNN with attention mechanism for MI-EEG decoding. IEEE Transactions on Neural Systems and Rehabilitation Engineering.
2. Link to source-code: https://github.com/Ma-Xinzhi/LightConvNet


## 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.