Practice Why Reduce Dimensions? (6.2.1) - Unsupervised Learning – Clustering & Dimensionality Reduction

Practice: Why Reduce Dimensions?

Lesson 6.2.1Unsupervised Learning – Clustering & Dimensionality Reduction

Practise this section

10 questions

Flashcard drill
4 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is meant by the curse of dimensionality?
Show hintHide hint
Think about how data points might spread out.
Question 2.
How does reducing dimensions improve computational cost?
Show hintHide hint
Consider how many features algorithms need to work with.
3Question 3.
What is the curse of dimensionality?
- Challenges caused by too few features
- Problems arising when data becomes sparse in high dimensions
- An increase in noise with more data features
Show hintHide hint
Think about the effect of having too many features.
4Question 4.
True or False: Dimensionality reduction can lead to overfitting.
- True
- False
Show hintHide hint
Consider how reducing features impacts model training.
Question 5.
Consider a high-dimensional dataset with 100 features. Discuss the potential impact this may have on a machine learning model and how dimensionality reduction could help.
Show hintHide hint
Think about the relationship between dimensions and data density.
Question 6.
In a practical application, how would you decide which features to retain or discard when reducing dimensions?
Show hintHide hint
What metrics indicate feature importance?

6 more questions in this section. Enroll free to practise them all.