Accuracy vs GM prevalence
Created on June 30|Last edited on June 30
Comment
This report shows the tradeoff between accuracy and GM prevalence for randomly generated datasets. Each scenario is a different way of generating random datasets.
The scatter plots are interactive, meaning that you can click on a point and you will be directed to the associated run. Each run corresponds to a specific dataset (that was randomly initialised) and trained from 100 different random weight initialisations.
Below each chart, there are two options:
- "all" displays all runs
- "with GM" displays only those runs where the GM was reached at least once during the 100 training trials
Scenario #1: 7 red, 5 blue, 3 hyperplanes
Scenario #2: 7 red, 5 blue, 2 hyperplanes
Add a comment