This is a suite of tools made available for neuroscience researchers to use a variety of M/EEG neural network architectures on their data.
- Source: https://github.com/arthurdehgan/meegnet
- Bug Reports: https://github.com/arthurdehgan/meegnet/issues
The package currently supports the following architectures:
- LF-CNN
- VAR-CNN
- EEGNet
For a full documentation of the package as well as tutorials on how to use the library, click the Readthedocs link.
Work in Progress
Prepare your data by following the instructions here
Learn the basics of how to train and evaluate using a pre-made network here
Maybe this package doesn’t suit your needs, in which case we can recommend similar packages with similar goals:
Work in Progress
Zubarev I, Zetter R, Halme HL, Parkkonen L. Adaptive neural network classifier for decoding MEG signals. Neuroimage. 2019 May 4;197:425-434. link
@article{Zubarev2019AdaptiveSignals., title = {{Adaptive neural network classifier for decoding MEG signals.}}, year = {2019}, journal = {NeuroImage}, author = {Zubarev, Ivan and Zetter, Rasmus and Halme, Hanna-Leena and Parkkonen, Lauri}, month = {5}, pages = {425--434}, volume = {197}, url = {https://linkinghub.elsevier.com/retrieve/pii/S1053811919303544 http://www.ncbi.nlm.nih.gov/pubmed/31059799}, doi = {10.1016/j.neuroimage.2019.04.068}, issn = {1095-9572}, pmid = {31059799}, keywords = {Brain–computer interface, Convolutional neural network, Magnetoencephalography} }
@article{Lawhern2018, author={Vernon J Lawhern and Amelia J Solon and Nicholas R Waytowich and Stephen M Gordon and Chou P Hung and Brent J Lance}, title={EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces}, journal={Journal of Neural Engineering}, volume={15}, number={5}, pages={056013}, url={http://stacks.iop.org/1741-2552/15/i=5/a=056013}, year={2018} }