Skip to main content
PProfileMatch
Read Play
← Path

Supervised Learning · Model Selection and Cross-Validation: Pick the Right Model Fairly

0 XP
  1. 1 current stop: learning
  2. 2 upcoming
  3. 3 upcoming
  4. 4 upcoming
  5. 5 upcoming

Finish after stop 5

Stop 1 of 5 · Bike park with five trails

Trick to keep in mind+3 XP

k folds means k models; each trains on everything except its own held-out fold.

K-fold splits the rows into k equal parts. In each round one part is held out for scoring and the rest is used for training. With 12 rows and 4 folds that is 4 models, each held out on 3 rows and trained on 9. Every row gets validated exactly once.

Read it once, then a question tests whether the trick stuck.