Unsupervised Learning
Clustering, dimensionality reduction, density estimation and anomaly detection.
Introduction
Unsupervised learning finds structure in data without labels. The three big families are clustering (grouping similar points), dimensionality reduction (compressing while preserving structure), and density / anomaly modeling (learning what "normal" looks like).
Modern representation learning — contrastive methods, autoencoders, self-supervised pretraining — sits on the same foundations and powers today's foundation models. Interviewers will probe how you'd choose k, why distances break in high dimensions, and when to reach for DBSCAN over k-means.
The 9 sections
Each section is a short read on one subject, with every answer written out. Work through them in order, or jump to the one you are weakest on.
- 01Clustering basicsHow does k-means work and what are its main limitations?69 questions4 easy32 medium33 hard
- 02Advanced clustering & densityLocal Outlier Factor (LOF) — how does it work?8 questions4 medium4 hard
- 03Distance & scaling considerationsHNSW — how does it work?6 questions6 hard
- 04Cluster evaluationHow do you evaluate anomaly detection?5 questions4 medium1 hard
- 05Linear dimensionality reductionPCA vs t-SNE vs UMAP — when do you use each?38 questions2 easy21 medium15 hard
- 06Anomaly & outlier detectionWhat are the main approaches to anomaly detection?26 questions8 medium18 hard
- 07Autoencoders & VAEsWhat is self-supervised learning and why does it matter?34 questions14 medium20 hard
- 08Topic modeling & textWhat is topic modeling and when do you use LDA?10 questions1 easy5 medium4 hard
- 09Recommender & associationCollaborative filtering — how does it use unsupervised methods?18 questions8 medium10 hard