Quiz di AI & Machine Learning: Cross-Validation

This quiz covers cross-validation, the standard way to estimate how a model will do on new data. It tests k-fold mechanics, choosing the right split for your data and the leakage mistakes that interviewers love to ask about.

Medio 10 domande ~6 minuti Superato con il 80%

Scegli una modalità

Stai giocando come ospite: accedi per salvare XP e serie.

Domanda di esempio

Domanda 1 di 10

You run 5-fold cross-validation on 1,000 rows. How many models are trained and how big is each validation fold?

Mostra la risposta

A. 5 models, 200 validation rows each The data is split into 5 folds of 200 rows. Each fold is the validation set once while a fresh model trains on the other 800 rows, so 5 models in total. One model per row would be leave-one-out.

Cosa copre questo quiz

  • How k-fold and leave-one-out split the data
  • Stratified, grouped and time-series splits
  • Leakage from preprocessing or oversampling before the split
  • Why tuning on CV scores needs nested CV or a test set
  • Reading and averaging fold scores

Domande frequenti

Serve un account?

No. Chiunque può giocare. Accedi per salvare XP, serie, badge e cronologia.

Posso rifarlo?

Sì. Il tuo miglior punteggio resta salvato, e domande e risposte vengono mescolate ogni volta.