kmeans_varpar(X,k)

Implementation of K-means with Variance Partitioning initialization

Version 1.0.1.0 (2,92 ko)
210 téléchargements
(0)
9 août 2017

Vous suivez désormais cette soumission

Implementation of K-means with Variance Partitioning initialization. Variance Partitioning initialization is a deterministic way of initializing the data centroids, thus producing results that are repeatable and reproducible, without having to resort to tricks like seeding the pseudorandom number generator.

Citation pour cette source

Stefan Philippo Pszczolkowski Parraguez (2026). kmeans_varpar(X,k) (https://fr.mathworks.com/matlabcentral/fileexchange/57229-kmeans_varpar-x-k), MATLAB Central File Exchange. Extrait(e) le .

Remerciements

Inspiré par : k-means++

Catégories

En savoir plus sur Cluster Analysis and Anomaly Detection dans Help Center et MATLAB Answers

Informations générales

Compatibilité avec les versions de MATLAB

  • Compatible avec toutes les versions

Plateformes compatibles

  • Windows
  • macOS
  • Linux
Ouvrir dans un nouvel onglet
Version Publié le Notes de version
1.0.1.0

Removed loop that made sure that the number of returned centrers is equal to the specified k. This is arguably not necessary and since variance partitioning provides a deterministic result, there is potential for getting trapped in an infinite loop.
Removed loop that made sure that the number of returned centrers is equal to the specified k. This is arguably not necessary and since variance partitioning provides a deterministic result, there is potential for getting trapped in an infinite loop.
1.0.0.0