EasyDeepLearn

When would you pick DBSCAN over k-means?

medium

Answer

  • Pick DBSCAN when clusters are non-convex or of very different densities, when you don't want to specify k, and when you want an explicit notion of noise/outliers. k-means struggles with irregular shapes and forces every point into a cluster.
  • DBSCAN needs two parameters: eps (neighborhood radius) and minsamples\operatorname{min}_{\mathrm{samples}}.
Check yourself — multiple choice
  • DBSCAN requires setting k explicitly
  • DBSCAN handles arbitrary-shape clusters and detects noise
  • k-means handles noise better than DBSCAN
  • DBSCAN cannot detect outliers

DBSCAN finds arbitrary shapes and labels low-density points as noise.

#clustering

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions