βœ… Quiz M2.02ΒΆ

Question

A model is overfitting when:

  • a) both the train and test errors are high

  • b) train error is low but test error is high

  • c) train error is high but the test error is low

  • d) both train and test errors are low

Question

Assuming that we have a dataset with little noise, a model is underfitting when:

  • a) both the train and test errors are high

  • b) train error is low but test error is high

  • c) train error is high but the test error is low

  • d) both train and test errors are low

Question

For a fixed training set, if we change a model parameter to give the model more flexibility, are we more likely to observe:

  • a) a wider difference between train and test errors

  • b) a reduction in the difference between train and test errors

  • c) an increase in the train error

  • d) a decrease in the train error

Question

For a fixed choice of model parameters, if we increase the number of labeled observations in the training set, are we more likely to observe:

  • a) a wider difference between train and test errors

  • b) a reduction in the difference between train and test errors

  • c) an increase in the train error

  • d) a decrease in the train error

Question

Polynomial models with a high degree parameter:

  • a) always have the best test error (but can be slow to train)

  • b) underfit more than linear regression models

  • c) get lower training error than lower degree polynomial models

  • d) are more likely to overfit than lower degree polynomial models

Question

One can always reach zero test error by:

  • a) choosing the model parameters to find the best overfitting/underfitting tradeoff

  • b) day-dreaming ;)