Demonstration of practical properties of "Robust Bi-Tempered Logistic Loss Based on Bregman Divergences", 2019,
Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren. Read manuscript. Link to GitHub

$
  • This trains a 2-layer neural network of size [10, 5] and visualizes the decision boundary above.
  • Colors indicate the class label.
  • You can drag & drop points on the canvas to see how the model handles noisy data points.
  • You can also auto-generate noise levels using the options on the right.
  • Please refresh the page when something breaks :)

Select noise type:

  • Decrease Temperature 1 to handle large margin noise.
  • Increase Temperature 2 to handle small margin noise.
  • Adjust Temperature 1 & 2 to handle random noise.

Adjust temperature of loss function:

Warmstart model parameters when data/temperature settings change?