0Pricing
Deep Learning Academy · Lesson

Calibrate Confidence

Make predicted probabilities trustworthy.

Confidence Is a Promise

When a model says 90 percent, it should be right about 90 percent of those times. Calibration measures whether that promise holds.

Overconfident by Default

Modern deep nets often output probabilities that are too high. They sound certain even when they are frequently wrong.

All lessons in this course

  1. Precision, Recall, F1 & ROC-AUC
  2. Confusion Matrices & Error Analysis
  3. Grad-CAM: See What the Model Looks At
  4. Calibrate Confidence
← Back to Deep Learning Academy