You've now seen two different ways to classify data: k-Nearest Neighbors, which uses proximity, and Decision Trees, which use a series of questions. Both are powerful, but they work in fundamentally different ways. Let's practice telling them apart.
Engagement Message
Ready to get started?
Type
Sort Into Boxes
Practice Question
Sort these core concepts into the algorithm they are most associated with.
Labels
- First Box Label: k-Nearest Neighbors
- Second Box Label: Decision Trees
First Box Items
- Euclidean distance
- Majority vote
- k value
Second Box Items
- Gini impurity
- Splitting data
- Root node
Type
Multiple Choice
Practice Question
In a k-NN model with k=5, you are classifying a new data point. Its five nearest neighbors have the following labels: [Blue, Red, Red, Blue, Red]. What will the model predict for the new data point?
A. Blue B. Red C. It cannot be determined. D. Both Blue and Red.
Suggested Answers
- A
- B - Correct
- C
- D
Type
Fill In The Blanks
Markdown With Blanks
A decision tree is used to decide if you should play tennis. The first question (the root node) is "Is the outlook sunny?". If the answer is yes, the next question is "Is the humidity high?".
