The GATE Grind

GATE Machine Learning: Dimensionality reduction and principal component analysis – Previous Year Questions

3 GATE previous year questions on Dimensionality reduction and principal component analysis (Machine Learning, Data Science and Artificial Intelligence) with answers and explanations, from every paper.

3 questions worth 4 marks in all (2 1-mark, 1 2-mark). Asked between 2024 and 2026, so you can see how the topic has been tested over time.

  1. GATE 2024 DA Q22 (1 mark, Multiple choice) – For any binary classification dataset, let S B Rd d and S W Rd d be the between-class and within-class scatter (covariance) matrices, respectively.…
  2. GATE 2025 DA Q60 (2 marks, Numerical answer) – Let D = \x(1), , x(n)\ be a dataset of n observations where each x(i) R100. It is given that i=1n x(i) = 0. The covariance matrix computed from D has…
  3. GATE 2026 DA Q11 (1 mark, Multiple choice) – For a classification problem, Principal Component Analysis (PCA) has been used to reduce the dimensionality of a feature space from 100 to 10. Which…