Machine learning functionality - clustering

[HussainAther]

Use signal processing metrics to create machine learning functionality for EEG-Notebooks and compare clustering algorithms. We can use scikit t-SNE optimization techniques (https://scikit-learn.org/stable/modules/manifold.html#optimizing-t-sne), Pyriemann Embedding (https://pyriemann.readthedocs.io/en/latest/auto_examples/ERP/plot_embedding_EEG.html#sphx-glr-auto-examples-erp-plot-embedding-eeg-py), diffusion_map (https://pydiffmap.readthedocs.io/en/master/reference/diffusion_map.html), and other ideas (anything else?)

Follow my work on Twitch: https://www.twitch.tv/hussainather

[HussainAther]

• [x] Show plots for different ML techniques (t-SNE, TangentSpace, Embedding).
• [x] Have presentation ready by 16:00 EST.

[HussainAther]

Finishing up the MLapproaches.ipynb file to turn it into a page of the documentation for the NeurotechX repository.

• [x] Add more background info on what this documentation is meant to be so the reader can understand.
• [x] Get the content finalized and tidied. Rearrange the cells into an organized order and make sure each of them can run on both sets of data.
• [x] Export the file as a .py file for sphinx gallery.
• [x] Make a PR. Follow the style of other pull requests.

[JohnGriffiths]

Awesome!

I suggest call the final file

examples/visual_n170/04r__n170_clustering.py

[HussainAther]

Thanks! Would you like me to add pyDiffMap to the requirements.txt file?

[JohnGriffiths]

@HussainAther I believe this is now summarized in the PR

https://github.com/NeuroTechX/eeg-notebooks/pull/58

We'll review that and resume comments there :)