ML2 NO CHOKE

In SVM, how does a large value of C affect the decision boundary?

• Smaller margin

• Larger margin

• Decrease overfitting

• No impact

What is a key advantage of Naïve Bayes?

• Processes all cases at root

• Handles real-valued parameters well

• Requires feature transformation

• Robust to irrelevant features

When is XGBoost recommended to be used?

• When good performance is needed at the cost of computation

• When model explainability is crucial

• When regression works well

• When overfitting is a big concern

Which ones are true?

• Bagging handles overfitting, Boosting reduces bias

• Bagging reduces bias, Boosting reduces variance

Which one is True?

• Bagging uses independent classifiers, Boosting uses sequential classifiers

• Bagging uses sequential classifiers, Boosting uses independent classifiers

Two stregths of SVM are:

• Can handle nonlinear feature interactions

• Can handle large feature space

• Can handle linear feature interactions

• Can handle small feature space

Two Disadvanteges of KNN

• Slow at query time

• Easily fooled by irrelevant attributes and the scale of the data

• Optimization and training required

• Complex Algorithm

Important XGBoost CON or Disadvantage:

• Leads to overfitting if hyperparameters are not tuned properly.

• Not Versatile

• Extremely Slow

• Cannot be used to extract variable importance.

LDA is ...

• Supervised

• Unsupervised

PCA is used for .... and LDA for ....

• PCA to reduce dimensions, LDA to perform the classification

• PCA to increase dimensions, LDA to perform the regression

• LDA to reduce dimensions, PCA to perform the classification

• PCA to reduce dimensions, LDA to perform the regression