Models Summary#
This page offers a summary of all braindecode implemented models. For more
information on each model, please consult the API.
Columns definitions:
Model: The name of the model.
Application: The application(s) the model is typically used for (e.g., Motor Imagery, P300, Sleep Staging). ‘General’ indicates applicability across multiple applications or no specific application focus.
Modality: The recording modality (bio-signal type) the model is designed and validated for, e.g. EEG, MEG, or sEMG. Most Braindecode models target EEG; a few support more than one modality (e.g. EEG, MEG).
Type: The model’s output interface.
Predictionindicates a supervised head that can be used for classification or regression, depending on the wrapper, loss, and target.Embeddingindicates a model that exposes an embedding representation through its documented public interface.Sampling Frequency: The data sampling rate (in Hertz) the model is designed for. Note that this might be adaptable depending on the specific dataset and application.
Categorization: models categorization based on the main building blocks used in the architecture. See Models Categorization page for more details.
- Hyperparameters: The mandatory hyperparameters required for instantiating the model class. These may include:
n_chans, number of channels/electrodes/sensors,
n_outputs, number of output classes or regression targets,
n_times, number of time points in the input window,
freq (Hz), sampling frequency,
chs_info, information about each individual EEG channel. Refer to
mne.Info(see its “chs” field for details)Also, n_times can be derived implicitly by providing both sfreq and input_window_seconds.
#Parameters: The approximate total number of trainable parameters in the model, calculated using a consistent configuration (see note below).
| Model | Application | Modality | Type | Categorization | Sampling Frequency (Hz) | #Parameters | Hyperparameters |
|---|---|---|---|---|---|---|---|
| ATCNet | General | EEG | Prediction | Convolution Recurrent Attention/Transformer | 250 | 113732 | n_chans n_outputs n_times |
| AttentionBaseNet | Motor Imagery | EEG | Prediction | Convolution Attention/Transformer | 250 | 3692 | n_chans n_outputs n_times |
| BDTCN | Normal Abnormal | EEG | Prediction | Convolution Recurrent | 100 | 456502 | n_chans n_outputs n_times |
| BIOT | Sleep Staging Epilepsy | EEG | Prediction | Foundation Model | 200 | 3183879 | n_chans n_outputs |
| CBraMod | General | EEG | Prediction Embedding | Foundation Model | 200 | 4924000 | n_outputs |
| CodeBrain | General | EEG | Prediction Embedding | Foundation Model Attention/Transformer | 200 | 15238802 | n_chans n_outputs n_times |
| ContraWR | Sleep Staging | EEG | Prediction Embedding | Convolution | 125 | 1160165 | n_chans n_outputs freq (Hz) |
| CTNet | Motor Imagery | EEG | Prediction | Convolution Attention/Transformer | 250 | 26900 | n_chans n_outputs n_times |
| Deep4Net | General | EEG | Prediction | Convolution | 250 | 282879 | n_chans n_outputs n_times |
| DeepSleepNet | Sleep Staging | EEG | Prediction | Convolution Recurrent | 256 | 24744837 | n_chans n_outputs |
| EEGConformer | General | EEG | Prediction | Convolution Attention/Transformer | 250 | 789572 | n_chans n_outputs n_times |
| EEGPT | General | EEG | Prediction | Foundation Model Attention/Transformer | 256 | 25477635 | n_chans n_outputs n_times |
| EEGInceptionERP | ERP SSVEP | EEG | Prediction | Convolution | 128 | 14926 | n_chans n_outputs |
| EEGInceptionMI | Motor Imagery | EEG | Prediction | Convolution | 250 | 558028 | n_chans n_outputs n_times |
| EEGITNet | Motor Imagery | EEG | Prediction | Convolution Recurrent | 125 | 5212 | n_chans n_outputs n_times |
| EEGNet | General | EEG | Prediction | Convolution | 128 | 2484 | n_chans n_outputs n_times |
| EEGNeX | Motor Imagery | EEG | Prediction | Convolution | 125 | 55940 | n_chans n_outputs n_times |
| EEGSym | Motor Imagery | EEG | Prediction | Convolution Channel | 250 | 299218 | n_chans n_outputs n_times freq (Hz) |
| EEGMiner | Emotion Recognition | EEG | Prediction | Convolution Interpretability | 128 | 7572 | n_chans n_outputs n_times freq (Hz) |
| EEGSimpleConv | Motor Imagery | EEG | Prediction | Convolution | 80 | 730404 | n_chans n_outputs freq (Hz) |
| EEGTCNet | Motor Imagery | EEG | Prediction | Convolution Recurrent | 250 | 4516 | n_chans n_outputs |
| Labram | General | EEG | Prediction Embedding | Convolution Foundation Model | 200 | 5866180 | n_chans n_outputs n_times |
| MSVTNet | Motor Imagery | EEG | Prediction | Convolution Recurrent Attention/Transformer | 250 | 75494 | n_chans n_outputs n_times |
| SCCNet | Motor Imagery | EEG | Prediction | Convolution | 125 | 12070 | n_chans n_outputs n_times freq (Hz) |
| SignalJEPA | Motor Imagery ERP SSVEP | EEG | Embedding | Convolution Channel Foundation Model | 128 | 3456882 | n_times chs_info |
| SignalJEPA_Contextual | Motor Imagery ERP SSVEP | EEG | Prediction | Convolution Channel Foundation Model | 128 | 3459184 | n_outputs n_times chs_info |
| SignalJEPA_PostLocal | Motor Imagery ERP SSVEP | EEG | Prediction | Convolution Channel Foundation Model | 128 | 16142 | n_chans n_outputs n_times |
| SignalJEPA_PreLocal | Motor Imagery ERP SSVEP | EEG | Prediction | Convolution Channel Foundation Model | 128 | 16142 | n_outputs n_times chs_info |
| SincShallowNet | Motor Imagery | EEG | Prediction | Convolution Interpretability | 250 | 21892 | n_chans n_outputs n_times freq (Hz) |
| ShallowFBCSPNet | General | EEG | Prediction | Convolution | 250 | 46084 | n_chans n_outputs n_times |
| SleepStagerBlanco2020 | Sleep Staging | EEG | Prediction | Convolution | 100 | 2845 | n_chans n_outputs n_times |
| SleepStagerChambon2018 | Sleep Staging | EEG | Prediction | Convolution | 128 | 5835 | n_chans n_outputs n_times freq (Hz) |
| AttnSleep | Sleep Staging | EEG | Prediction | Convolution Attention/Transformer | 100 | 719925 | n_chans n_outputs n_times freq (Hz) |
| SPARCNet | Epilepsy | EEG | Prediction | Convolution | 200 | 1141921 | n_chans n_outputs n_times |
| SyncNet | Emotion Recognition Alcoholism | EEG | Prediction | Interpretability | 256 | 554 | n_chans n_outputs n_times |
| TSception | Emotion Recognition | EEG | Prediction | Convolution | 256 | 2187206 | n_chans n_outputs n_times freq (Hz) |
| TIDNet | General | EEG | Prediction | Convolution | 250 | 240404 | n_chans n_outputs n_times |
| USleep | Sleep Staging | EEG | Prediction | Convolution | 128 | 2482011 | n_chans n_outputs n_times freq (Hz) |
| FBCNet | Motor Imagery | EEG | Prediction | Convolution FilterBank | 250 | 11812 | n_chans n_outputs n_times freq (Hz) |
| FBMSNet | Motor Imagery | EEG | Prediction | Convolution FilterBank | 250 | 16231 | n_chans n_outputs n_times freq (Hz) |
| MetaNeuromotorHand | Handwriting (sEMG) | sEMG | CTC Sequence | Convolution Attention/Transformer | 2000 | 1021284 | n_chans n_outputs n_times freq (Hz) |
| EMG2QwertyNet | Touch typing (sEMG) | sEMG | CTC Sequence | Convolution | 2000 | 5293315 | n_chans n_outputs n_times freq (Hz) |
| FBLightConvNet | Motor Imagery | EEG | Prediction | Convolution FilterBank | 250 | 6596 | n_chans n_outputs n_times freq (Hz) |
| IFNet | Motor Imagery | EEG | Prediction | Convolution FilterBank | 250 | 9860 | n_chans n_outputs n_times freq (Hz) |
| BrainModule | Speech Decoding | EEG MEG | Prediction | Convolution | 250 | 6186909 | n_chans n_outputs n_times freq (Hz) |
| PBT | General | EEG | Prediction | Foundation Model | 250 | 818948 | n_chans n_outputs n_times |
| SSTDPN | Motor Imagery | EEG | Prediction | Convolution Attention/Transformer | 250 | 19502 | n_chans n_outputs n_times |
| BENDR | General | EEG | Prediction Embedding | Foundation Model Convolution | 250 | 157141049 | n_chans n_times n_outputs |
| LUNA | General | EEG | Prediction Embedding | Convolution Channel Foundation Model | 128 | 7100731 | n_chans n_times freq (Hz) chs_info |
| MEDFormer | General | EEG | Prediction | Foundation Model Convolution | 250 | 5313924 | n_chans n_outputs n_times |
| REVE | General | EEG | Prediction | Foundation Model Attention/Transformer | 200 | 69481476 | n_outputs n_times n_chans |
| DGCNN | Emotion Recognition | EEG | Prediction | Graph Neural Network Channel | 128 | 1037385 | n_chans n_outputs n_times chs_info |
| InterpolatedBENDR | General | EEG | Prediction Embedding | Foundation Model Convolution Channel | 250 | 157143101 | chs_info n_outputs n_times |
| InterpolatedBIOT | Sleep Staging Epilepsy | EEG | Prediction | Foundation Model Channel | 200 | 3184101 | chs_info n_outputs n_times freq (Hz) |
| InterpolatedEEGPT | General | EEG | Prediction | Foundation Model Attention/Transformer Channel | 256 | 25323137 | chs_info n_outputs n_times |
| InterpolatedLaBraM | General | EEG | Prediction Embedding | Convolution Foundation Model Channel | 200 | 5866196 | chs_info n_outputs n_times |
| InterpolatedSignalJEPA | Motor Imagery ERP SSVEP | EEG | Embedding | Convolution Channel Foundation Model | 128 | 3456882 | chs_info |
| TCFormer | Motor Imagery | EEG | Classification | Convolution Attention/Transformer | 250 | 77820 | n_chans n_outputs n_times |
| EEGDINO | General | EEG | Classification | Foundation Model Attention/Transformer | 200 | 4539698 | n_chans n_outputs n_times |
| STEEGFormer | General | EEG | Classification | Attention/Transformer Foundation Model | 250 | 25305604 | n_chans n_outputs n_times |
The parameter counts shown in the table were calculated using consistent hyperparameters for models within the same paradigm, based largely on Braindecode’s default implementation values. These counts provide a relative comparison but may differ from those reported in the original publications due to variations in specific architectural details, input dimensions used in the paper, or calculation methods.
We are continually expanding this collection and welcome contributions! If you have implemented a model relevant to EEG, EcoG, or MEG analysis, consider adding it to Braindecode.