Statements (24)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:algorithm
|
gptkbp:advantage |
faster convergence
better initial centroid selection improved clustering quality |
gptkbp:alsoKnownAs |
K-means plus plus
|
gptkbp:category |
unsupervised learning
|
gptkbp:complexity |
O(k n)
|
gptkbp:field |
gptkb:machine_learning
data mining |
https://www.w3.org/2000/01/rdf-schema#label |
K-means++
|
gptkbp:improves |
gptkb:K-means
|
gptkbp:initializationMethod |
probabilistic selection of centroids
|
gptkbp:introduced |
gptkb:David_Arthur
Sergei Vassilvitskii |
gptkbp:introducedIn |
2007
|
gptkbp:publishedIn |
Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
|
gptkbp:purpose |
cluster analysis
|
gptkbp:reduces |
within-cluster sum of squares
sensitivity to initial seeds |
gptkbp:relatedTo |
gptkb:K-means
gptkb:Lloyd's_algorithm |
gptkbp:usedFor |
partitioning data into clusters
|
gptkbp:bfsParent |
gptkb:K-means
|
gptkbp:bfsLayer |
7
|