Dimensionality Reduction Algorithms MCQs

1. Dimensionality reduction techniques are used to:

a. Increase the number of features in a dataset

b. Reduce the number of features in a dataset

c. Scale the features in a dataset

d. Balance the class distribution in a dataset


Answer: b. Reduce the number of features in a dataset


2. Principal Component Analysis (PCA) is a dimensionality reduction technique that:

a. Maximizes the variance in the original features

b. Minimizes the correlation between features

c. Creates new features that are linear combinations of the original features

d. Normalizes the features in a dataset


Answer: c. Creates new features that are linear combinations of the original features


3. PCA finds the directions of maximum variance in the data by:

a. Singular Value Decomposition (SVD)

b. Eigendecomposition

c. Correlation analysis

d. T-distributed Stochastic Neighbor Embedding (t-SNE)


Answer: b. Eigendecomposition


4. Linear Discriminant Analysis (LDA) is a dimensionality reduction technique that:

a. Maximizes the variance in the original features

b. Minimizes the correlation between features

c. Creates new features that are linear combinations of the original features

d. Maximizes the separability between different classes


Answer: d. Maximizes the separability between different classes


5. Which dimensionality reduction technique is suitable for supervised learning tasks?

a. PCA

b. LDA

c. t-SNE

d. Autoencoder


Answer: b. LDA


6. t-SNE (t-distributed Stochastic Neighbor Embedding) is a dimensionality reduction technique that:

a. Preserves the global structure of the data

b. Reduces the dimensionality based on class labels

c. Focuses on preserving local similarities between data points

d. Performs feature extraction using neural networks


Answer: c. Focuses on preserving local similarities between data points


7. Non-negative Matrix Factorization (NMF) is a dimensionality reduction technique that:

a. Finds orthogonal features that capture the most variance

b. Creates non-linear combinations of the original features

c. Performs feature extraction using neural networks

d. Decomposes a non-negative matrix into two non-negative matrices


Answer: d. Decomposes a non-negative matrix into two non-negative matrices


8. Independent Component Analysis (ICA) is a dimensionality reduction technique that:

a. Finds orthogonal features that capture the most variance

b. Creates non-linear combinations of the original features

c. Performs feature extraction using neural networks

d. Separates a mixture of signals into statistically independent components


Answer: d. Separates a mixture of signals into statistically independent components


9. Manifold Learning is a dimensionality reduction technique that:

a. Creates non-linear combinations of the original features

b. Decomposes a non-negative matrix into two non-negative matrices

c. Finds orthogonal features that capture the most variance

d. Preserves the intrinsic structure of the data in a lower-dimensional space


Answer: d. Preserves the intrinsic structure of the data in a lower-dimensional space


10. Which dimensionality reduction technique can handle both linear and non-linear relationships in the data?

a. PCA

b. LDA

c. t-SNE

d. NMF


Answer: c. t-SNE


11. Which dimensionality reduction technique is based


on maximizing the mutual information between the transformed features and the target variable?

a. PCA

b. LDA

c. t-SNE

d. Mutual Information-based Feature Selection


Answer: b. LDA


12. Which dimensionality reduction technique is based on preserving the pairwise distances between data points?

a. PCA

b. LDA

c. t-SNE

d. NMF


Answer: c. t-SNE


13. Which dimensionality reduction technique is commonly used in image and signal processing?

a. PCA

b. LDA

c. t-SNE

d. ICA


Answer: d. ICA


14. Which dimensionality reduction technique can handle both numerical and categorical features?

a. PCA

b. LDA

c. t-SNE

d. Multiple Correspondence Analysis


Answer: d. Multiple Correspondence Analysis


15. Which dimensionality reduction technique is computationally expensive and suitable for small to medium-sized datasets?

a. PCA

b. LDA

c. t-SNE

d. NMF


Answer: c. t-SNE


16. Which dimensionality reduction technique can be used for feature extraction and denoising of data?

a. PCA

b. LDA

c. t-SNE

d. Autoencoder


Answer: d. Autoencoder


17. Which dimensionality reduction technique is based on the assumption that the data lies on a low-dimensional manifold embedded in a high-dimensional space?

a. PCA

b. LDA

c. t-SNE

d. Manifold Learning


Answer: d. Manifold Learning


18. Which dimensionality reduction technique is suitable for outlier detection and novelty detection?

a. PCA

b. LDA

c. t-SNE

d. Isolation Forest


Answer: d. Isolation Forest


19. Which dimensionality reduction technique is based on maximizing the variance in the transformed features?

a. PCA

b. LDA

c. t-SNE

d. ICA


Answer: a. PCA


20. Which dimensionality reduction technique is suitable for feature selection based on the statistical dependence between features and the target variable?

a. PCA

b. LDA

c. t-SNE

d. Mutual Information-based Feature Selection


Answer: d. Mutual Information-based Feature Selection


21. Which dimensionality reduction technique can be used for visualization of high-dimensional data?

a. PCA

b. LDA

c. t-SNE

d. NMF


Answer: c. t-SNE


22. Which dimensionality reduction technique is based on finding the optimal low-dimensional representation that minimizes the reconstruction error of the original data?

a. PCA

b. LDA

c. t-SNE

d. Autoencoder


Answer: d. Autoencoder


23. Which dimensionality reduction technique is suitable for text mining and natural language processing tasks?

a. PCA

b. LDA

c. t-SNE

d. Latent Semantic Analysis


Answer: d. Latent Semantic Analysis


24. Which dimensionality reduction technique is based on linear projections of the data onto a lower-dimensional subspace?

a. PCA

b. LDA

c. t-SNE

d. ICA


Answer: a. PCA


25. Which dimensionality reduction technique can handle categorical variables and preserve the associations between them?

a. PCA

b. LDA

c. t-SNE

d. Multiple Correspondence Analysis


Answer: d. Multiple Correspondence Analysis


26. Which dimensionality reduction technique is suitable for clustering analysis and outlier detection?

a. PCA

b. LDA

c. t-SNE

d. Isomap


Answer: d. Isomap


27. Which dimensionality reduction technique is based on maximizing the Fisher's discriminant ratio between classes?

a. PCA

b. LDA

c. t-SNE

d. Canonical Correlation Analysis


Answer: b. LDA


28. Which dimensionality reduction technique is suitable for exploring the relationships between multiple variables?

a. PCA

b. LDA

c. t-SNE

d. Factor Analysis


Answer: d. Factor Analysis


29. Which dimensionality reduction technique is based on clustering similar data points into groups and assigning representative prototypes?

a. PCA

b. LDA

c. t-SNE

d. K-Means Clustering


Answer: d. K-Means Clustering


30. Which dimensionality reduction technique is based on optimizing a non-linear manifold that preserves the local neighborhood relationships between data points?

a. PCA

b. LDA

c. t-SNE

d. Isomap


Answer: d. Isomap