Login to unlock
Machine Learning Fundamentals · Phase 5: Classification · Distance & Tree Methods

Distance & Tree Methods — Checkpoint Quiz

Checkpoint quiz 3 questions
Back to course

Check your understanding of this module before moving on.

?

Checkpoint quiz 3 questions

A quick check on this module's key ideas before you move on
0/3
Question 01

Why does KNN require feature scaling, while a decision tree generally doesn't?

B is correct. Distance formulas sum differences across all features, so a feature with a huge numeric range will dominate the calculation. Tree splits just compare a feature to a threshold, so the scale of the numbers doesn't change which split point is chosen.
Question 02

What happens as K increases in K-Nearest Neighbors?

B is correct. A larger K averages over more neighbors, smoothing out noise (lower variance) but eventually washing out genuine local structure (higher bias) if K gets too large.
Question 03

A decision tree's Gini impurity for a group is 0. What does this mean?

B is correct. Gini impurity measures the probability that two randomly chosen points from the group have different labels. If every point is the same class, that probability is 0.