Dimensionality Reduction Techniques Quiz

1. Linear Discriminant Analysis (LDA) is a supervised technique that maximizes the separation between class means.

True

False

2. Kernel PCA allows for nonlinear dimensionality reduction by implicitly mapping data to a higher-dimensional space.

True

False

Submit

4. Which dimensionality reduction technique is most suitable for text data and sparse matrices?

T-SNE

Latent Semantic Analysis (LSA)

Autoencoders

Kernel PCA

5. Singular Value Decomposition (SVD) is the mathematical foundation underlying PCA.

True

False

Submit

7. Which method selects features based on their importance scores from a trained model?

Filter-based selection

Wrapper-based selection

Embedded selection

Statistical correlation

8. UMAP is a dimensionality reduction technique that preserves both global and local structure better than t-SNE.

True

False

Submit

10. Which technique is best suited for preserving local neighborhood structure in high-dimensional data?

PCA

T-SNE

Random Projection

Truncated SVD

11. What is the primary goal of dimensionality reduction in machine learning?

Increase the number of features

Reduce feature space while preserving data variance

Eliminate all categorical variables

Replace missing values automatically

12. What percentage of variance is typically retained when selecting principal components in PCA?

50–60%

70–80%

90–95%

100%

Submit

14. Which dimensionality reduction technique is unsupervised and nonlinear?

Linear Discriminant Analysis (LDA)

T-SNE

Principal Component Analysis (PCA)

Recursive Feature Elimination (RFE)

Submit

16. What does the 'curse of dimensionality' refer to?

The difficulty of interpreting high-dimensional data

Performance degradation due to too many features

The computational cost of feature scaling

The requirement for exponentially more data as dimensions increase

17. In PCA, the components are orthogonal, meaning they are uncorrelated with each other.

True

False

Submit

19. Which of the following is NOT an advantage of dimensionality reduction?

Reduced computational complexity

Improved model interpretability

Always increases model accuracy

Mitigates the curse of dimensionality

Submit

DataAI Dimensionality Reduction Techniques Quiz

1. Linear Discriminant Analysis (LDA) is a supervised technique that maximizes the separation between class means.

2.

What first name or nickname would you like us to use?

2. Kernel PCA allows for nonlinear dimensionality reduction by implicitly mapping data to a higher-dimensional space.

3. In manifold learning, the goal is to uncover the low-dimensional ____ structure underlying high-dimensional data.

4. Which dimensionality reduction technique is most suitable for text data and sparse matrices?

5. Singular Value Decomposition (SVD) is the mathematical foundation underlying PCA.

6. The scree plot in PCA shows the ____ explained by each principal component.

7. Which method selects features based on their importance scores from a trained model?

8. UMAP is a dimensionality reduction technique that preserves both global and local structure better than t-SNE.

9. Feature scaling is ____ before applying PCA to ensure all features contribute equally.

10. Which technique is best suited for preserving local neighborhood structure in high-dimensional data?

11. What is the primary goal of dimensionality reduction in machine learning?

12. What percentage of variance is typically retained when selecting principal components in PCA?

13. An autoencoder reduces dimensionality by learning a compressed ____ representation through an encoder-decoder architecture.

14. Which dimensionality reduction technique is unsupervised and nonlinear?

15. Feature selection differs from feature extraction because selection ____ existing features while extraction creates new ones.

16. What does the 'curse of dimensionality' refer to?

17. In PCA, the components are orthogonal, meaning they are uncorrelated with each other.

18. T-SNE is primarily used for data ____ and exploring cluster structures.

19. Which of the following is NOT an advantage of dimensionality reduction?

20. Principal Component Analysis (PCA) works by finding linear combinations of features that maximize ____.