← All topics
Quiz: Regularisation (Ridge and Lasso): questions with answers
10 questions, each with the answer and a short explanation.
Take the timed quiz + get a certificate →- Q1. A model has low training error but very high error on new data. What is this called?
- Q2. What does Ridge regression add to the ordinary MSE loss?
- Q3. As the Ridge penalty λ increases, what happens to the TRAINING error?
- Q4. Which method can set some weights to exactly zero, acting as feature selection?
- Q5. What does this print? (code)
- Q6. How should you choose the penalty strength λ?
- Q7. What does this print? (code)
- Q8. In scikit-learn's LogisticRegression, you change C from 1.0 to 0.01. What happens?
- Q9. Why must features be scaled before Ridge or Lasso?
- Q10. The degree-9 model with λ = 100 had high training AND validation error. Why?