More complex models

A$.$ have better generalization performance

B$.$ are easier to train than simpler models

C$.$ tend to overfit more

D$.$ are very interpretable

Which is NOT a technique for avoiding overfitting in tree induction?

A$.$ Grow the tree only of there is significant improvement in information gain.

B$.$ Control tree size by controlling the number of training instances at a leaf node.

C$.$ Reduce tree size by cutting off branches in a fully$-$grown tree.

D$.$ Select tree size by training a model on validation data.

Learning curves

A$.$ are used to select an optimal parameter complexity

B$.$ can illustrate whether obtaining more data would be a good investment

C$.$ are equivalent to fitting curves

D$.$ plot true positive rate vs false positive rate

Logistic regression is a model used to predict a outcome.

A$.$ linear, continuous

B$.$ linear, categorical

C$.$ nonlinear, continuous

D$.$ nonlinear, categorical

Which of the following is NOT true about logistic regression?

A$.$ Logistic regression can be used to predict the probability of membership in a certain class.

B$.$ Logistic regression takes a categorical target variable in training data.

C$.$ Training a logistic regression with scikit$-$learn package requires all predictors as numeric.

D$.$ The linear output of the mathematical function in a logistic regression represents the odds

of positive class membership.

Which of the following does not describe SVM $($support vector machine$)?$

A$.$ SVM is a supervised learning method.