Create a supervised Learning Problem
As an evaluation person I want to compare embeddings coming from different signal processing methods so that we can identify the most promising one.
Comments
- we need an explanation of all the annotations in the dataset and identify the labels that we want to predict
- we want to collect as much data as possible from all the experiments (4 or 5 experiments)
- we need the data in a format that is easy to read and put it somewhere (Git LFS?)
- NMF and Linear Regression might be an okayish baseline model