Hubert Banville

New dataset class for time-frequency representations

5

Although a lot of the architectures in the literature use raw EEG time series as input, some work has focused on using time-frequency representations instead. This is the case for...

As mentioned in #288, we could uniformize the Dataset classes API a bit more, which would allow us to provide parallel loading to all datasets by default. For instance, we...

Standardizing the preprocessing pipeline for large datasets

3

The pipeline we use in most of the examples is not well adapted to large datasets, as the operations are applied sequentially to all the recordings at once (sleep staging:...

[WIP] Decoding tutorial

1

This PR introduces a new tutorial example on EEG decoding approaches used in eeg-notebooks that I've been working on with @JadinTredup during the BrainHackON coding sprint. It is still in...