1. What is dimensionality reduction primarily used for?
(A) Reducing the number of features
(B) Increasing data size
(C) Data labeling
(D) Data duplication
2. Which problem is caused by high dimensional data?
(A) High accuracy
(B) Underfitting
(C) Overfitting
(D) Data balance
3. Which technique is commonly used for dimensionality reduction?
(A) PCA
(B) K-Means
(C) Apriori
(D) Naive Bayes
4. What does PCA stand for?
(A) Predictive Component Analysis
(B) Partial Component Algorithm
(C) Pattern Classification Approach
(D) Principal Component Analysis
5. PCA transforms data into:
(A) Independent variables
(B) Uncorrelated components
(C) Dependent variables
(D) Labeled classes
6. Which dimensionality reduction technique is supervised?
(A) PCA
(B) LDA
(C) ICA
(D) Autoencoder
7. What does LDA stand for?
(A) Linear Dimensional Analysis
(B) Logical Data Analysis
(C) Linear Discriminant Analysis
(D) Latent Data Algorithm
8. Which method maximizes class separability?
(A) LDA
(B) PCA
(C) ICA
(D) K-Means
9. Which technique is nonlinear?
(A) PCA
(B) t-SNE
(C) LDA
(D) Linear Regression
10. Which technique is mainly used for visualization?
(A) PCA
(B) LDA
(C) t-SNE
(D) ICA
11. Which method focuses on statistical independence?
(A) PCA
(B) LDA
(C) ICA
(D) Autoencoder
12. Which dimensionality reduction method uses neural networks?
(A) PCA
(B) LDA
(C) ICA
(D) Autoencoder
13. Which issue is reduced by dimensionality reduction?
(A) Curse of dimensionality
(B) Variance
(C) Bias
(D) Label noise
14. Which technique preserves maximum variance?
(A) LDA
(B) ICA
(C) t-SNE
(D) PCA
15. What happens if too many dimensions are removed?
(A) Improved accuracy always
(B) Better interpretability only
(C) Increased data size
(D) Loss of important information
16. Which method preserves local structure of data?
(A) PCA
(B) t-SNE
(C) LDA
(D) Linear Regression
17. Which is NOT a dimensionality reduction technique?
(A) PCA
(B) K-Means
(C) LDA
(D) Autoencoder
18. Which dimensionality reduction technique works best with labeled data?
(A) PCA
(B) t-SNE
(C) LDA
(D) ICA
19. Which metric is used to select principal components?
(A) Variance
(B) Support
(C) Accuracy
(D) Confidence
20. Which statement about dimensionality reduction is TRUE?
(A) It increases computational cost
(B) It always improves accuracy
(C) It helps reduce noise
(D) It replaces feature engineering