MML-14-13: Kernel PCA & Non-Linear Manifold Projections – Practice Quiz

30 worked single-select and multiselect questions on Kernel PCA & Non-Linear Manifold Projections. Cognitive level: Tier 2–4. Prerequisites: QS 14.12.

Learning objectives: Construct feature-map kernels and Gram matrices; Center training and test kernels consistently; Normalize Gram eigenvectors into unit feature directions; Compute training and out-of-sample component scores; Analyze kernel limits and computational cost; Distinguish feature-space projections from original-input preimages.

Each item is self-contained, with calculations, model diagnostics and explanations of every distractor. Study references: scikit-learn decomposition guide; Mathematics for Machine Learning.