Version (1.74 KB) by Laurent S
Cluster multivariate data using the k-means++ algorithm.
Updated 11 Feb 2013

View License

An efficient implementation of the k-means++ algorithm for clustering multivariate data. It has been shown that this algorithm has an upper bound for the expected value of the total intra-cluster distance which is log(k) competitive. Additionally, k-means++ usually converges in far fewer than vanilla k-means.

Cite As

Laurent S (2024). k-means++ (https://www.mathworks.com/matlabcentral/fileexchange/28804-k-means), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2012b
Compatible with any release
Platform Compatibility
Windows macOS Linux
Find more on Statistics and Machine Learning Toolbox in Help Center and MATLAB Answers

Inspired by: Kmeans Clustering

Inspired: kmeans_varpar(X,k), Sparsified K-Means

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes

Fixed bug with 1D datasets (thanks Xiaobo Li).

Improved handling of overclustering (thanks Sid S) and added a screenshot.

Small bugfix.

Removed dependency on randi for R2008a or lower (thanks Cassie).

Even faster, even less code and also fixed a few small bugs.