EasyDeepLearn

What is hierarchical clustering and when is it useful?

medium

Answer

  • It builds a tree (dendrogram) of nested clusters, either agglomerative (bottom-up: merge closest clusters) or divisive (top-down).
  • You cut the tree at a chosen height to get k clusters.
  • Useful when you want to explore cluster structure at multiple scales, or when you don't know k in advance and want a visual.
  • Downside: O(n2)O(n^{2}) memory, so it doesn't scale beyond ~10k points.
Check yourself — multiple choice
  • It scales linearly to millions of points
  • It produces a dendrogram and works well on smaller datasets
  • It requires k in advance
  • It only supports divisive splitting

Hierarchical clustering yields a dendrogram; O(n2)O(n^{2}) memory limits scale.

#clustering

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions