Article From:https://www.cnblogs.com/wangziyan/p/9060428.html

Clustering(Clustering)

Partitioning Methods:

  K-Means

  Saquential Leader

  Model Based Methods

  Density Based Methods

Hierachical Methods

 

Unsupervised Learning(Unsupervised learning)

  No labels

  Data driven

Part of the special need to be paid attention to:

arbitrary shapeHandling all kinds of shapes: noise and outlier noise, outliers processing power

———————————————————————

K-meansalgorithm

Evaluation

 The explanation is mainly about the effect of spherical data, which may be problematic for other effects.

Silhoustte

 

Leave a Reply

Your email address will not be published. Required fields are marked *