Machine learning on electrophysiology EEG signals

Course at AI4Health school 2021

In this course you will learn about state-of-the-art machine learning approaches for EEG and MEG signals. You will do so with MNE-Python which has become a reference tool to process MEG/EEG/sEEG/ECoG data in Python, as well as the scikit-learn library. You will learn to predict what people attend to given their brain activity or look at predicting sleep stages from clinical EEG data. The materials consist of slides in PDF and Jupyter notebooks using public datasets.

Inspiration for this tutorial was taken from the MNE-Python and braindecode sleep staging examples, as well as the mne-torch repository.

Open this tutorial in Google Colab

Running locally

To run this tutorial locally, make sure the repo has been cloned on your machine, and that the required packages are installed in a Python environment (3.6 or above). The packages can be installed by running:

pip install -r requirements.txt

Authors

• Alexandre Gramfort, Inria
• Hubert Banville, Inria & Interaxon
• Richard Höchenberger, Inria