Models Summary#

This page offers a summary of many implemented models. Please note that this list may not be exhaustive. For the definitive and most current list, including detailed class documentation, please consult the API documentation.

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. See the “Submit a New Model” section below for details.

Braindecode Models

Visualization comparing the models based on their total number of parameters (left plot) and the primary experimental paradigm they were designed for (right plot).#

Columns definitions:
  • Model: The name of the model.

  • Paradigm: The paradigm(s) the model is typically used for (e.g., Motor Imagery, P300, Sleep Staging). ‘General’ indicates applicability across multiple paradigms or no specific paradigm focus.

  • Type: The model’s primary function (e.g., Classification, Regression, Embedding).

  • Freq (Hz): The data sampling rate (in Hertz) the model is designed for. Note that this might be adaptable depending on the specific dataset and application.

  • Hyperparameters: The mandatory hyperparameters required for instantiating the model class. These may include n_chans (number of channels), n_outputs (number of output classes or regression targets), n_times (number of time points in the input window), or sfreq (sampling frequency). 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 Paradigm Type Freq(Hz) Hyperparameters #Parameters
ATCNet General Classification 250 n_chans, n_outputs, n_times 113732
AttentionBaseNet Motor Imagery Classification 250 n_chans, n_outputs, n_times 3692
BDTCN Normal/Abnormal Classification 100 n_chans, n_outputs, n_times 456502
BIOT Sleep Staging Epilepsy Classification 200 n_chans, n_outputs 3183879
ContraWR Sleep Staging Classification, Embedding 125 n_chans, n_outputs, sfreq 1160165
CTNet Motor Imagery Classification 250 n_chans, n_outputs, n_times 26900
Deep4Net Motor Imagery Classification 250 n_chans, n_outputs, n_times 282879
DeepSleepNet Sleep Staging Classification 256 n_chans, n_outputs 24744837
EEGConformer General Classification 250 n_chans, n_outputs, n_times 789572
EEGInceptionERP ERP SSVEP Classification 128 n_chans, n_outputs 14926
EEGInceptionMI Motor Imagery Classification 250 n_chans, n_outputs, n_times 558028
EEGITNet Motor Imagery Classification 125 n_chans, n_outputs, n_times 5212
EEGNetv1 General Classification 128 n_chans, n_outputs, n_times 3052
EEGNetv4 General Classification 128 n_chans, n_outputs, n_times 2484
EEGNeX Motor Imagery Classification 125 n_chans, n_outputs, n_times 55940
EEGMiner Emotion Recognition Classification 128 n_chans, n_outputs, n_times, sfreq 7572
EEGResNet General Classification 250 n_chans, n_outputs, n_times 247484
EEGSimpleConv Motor Imagery Classification 80 n_chans, n_outputs, sfreq 730404
EEGTCNet Motor Imagery Classification 250 n_chans, n_outputs 4516
Labram General Classification, Embedding 200 n_chans, n_outputs, n_times 5866180
MSVTNet Motor Imagery Classification 250 n_chans, n_outputs, n_times 75494
SCCNet Motor Imagery Classification 125 n_chans, n_outputs, n_times, sfreq 12070
SignalJEPA Motor Imagery ERP SSVEP Embedding 128 n_times, chs_info 3456882
SignalJEPA_Contextual Motor Imagery ERP SSVEP Classification 128 n_outputs, n_times, chs_info 3459184
SignalJEPA_PostLocal Motor Imagery ERP SSVEP Classification 128 n_chans, n_outputs, n_times 16142
SignalJEPA_PreLocal Motor Imagery ERP SSVEP Classification 128 n_outputs, n_times, chs_info 16142
SincShallowNet Motor Imagery Classification 250 n_chans, n_outputs, n_times, sfreq 21892
ShallowFBCSPNet Motor Imagery Classification 250 n_chans, n_outputs, n_times 46084
SleepStagerBlanco2020 Sleep Staging Classification 100 n_chans, n_outputs, n_times 2845
SleepStagerChambon2018 Sleep Staging Classification 128 n_chans, n_outputs, n_times, sfreq 5835
SleepStagerEldele2021 Sleep Staging Classification 100 n_chans, n_outputs, n_times, sfreq 719925
SPARCNet Epilepsy Classification 200 n_chans, n_outputs, n_times 1141921
SyncNet Emotion Recognition Alcoholism Classification 256 n_chans, n_outputs, n_times 554
TSceptionV1 Emotion Recognition Classification 256 n_chans, n_outputs, n_times, sfreq 2187206
TIDNet General Classification 250 n_chans, n_outputs, n_times 240404
USleep Sleep Staging Classification 128 n_chans, n_outputs, n_times, sfreq 2482011
FBCNet Motor Imagery Classification 250 n_chans, n_outputs, n_times, sfreq 11812
FBMSNet Motor Imagery Classification 250 n_chans, n_outputs, n_times, sfreq 16231
FBLightConvNet Motor Imagery Classification 250 n_chans, n_outputs, n_times, sfreq 6596
IFNet Motor Imagery Classification 250 n_chans, n_outputs, n_times, sfreq 9860

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.

Submit a new model#

Want to contribute a new model to Braindecode? Great! You can propose a new model by opening an issue (please include a link to the relevant publication or description) or, even better, directly submit your implementation via a pull request. We appreciate your contributions to expanding the library!