SchoolWhool
Quizzes and saved progress, freeSign in freeSign in

ML 5.1Lesson outlineLesson 1 of 5 in Module 5

The Confusion Matrix, Precision and Recall

Count the four outcomes, derive the rates from them, and see accuracy fail.

Video in production.

Lesson outline: The Confusion Matrix, Precision and Recall

In this lesson9 parts

  1. 01Two mistakes of one kind
  2. 02A prediction for every training tumor
  3. 03Choosing by accuracy
  4. 04Four cells, twelve tumors
  5. 05Rates from the cells
  6. 06Which number the problem needs
  7. 07Where accuracy and precision mislead
  8. 08Code
  9. 09Recap, your challenge, and what comes next

Builds on

This lesson stands on its own. These go deeper into what it uses.

Next steps: The Confusion Matrix, Precision and Recall

Next lesson · 5.2Thresholds, ROC and AUCTreat a classifier's output as a score, read the trade every threshold makes, and compare models across all thresholds at once.Start 5.2