K-Means Clustering

noun

say it: “KAY MEENZ KLUS-ter-ing” /ˈkeɪ ˈminz ˈklʌstərɪŋ/

A method that sorts examples into a chosen number of groups by repeatedly assigning each to the nearest group center and then moving the centers.

What is k-means clustering?

K-means clustering splits examples into k groups, where you choose k. It places k centers, puts each example with its nearest center, moves each center to the middle of its group, and repeats until nothing changes. It needs scaled features, because it measures distance.

In a sentence

  • “Each round of k-means clustering moved the centers a little less.”
  • “K-means clustering with k=3 found the café's commuters, students and weekend families.”

Level: Journeyman · More AI Basics terms at this level

Updated