Hierarchical clusters

Hierarchical clusters are sets

of nested clusters that are organized as a tree, where each node in the tree

represents a cluster and its sub-nodes represent the sub-clusters. The root

of the tree represents the cluster that contains all the objects. There are

two main approaches in hierarchical clustering the agglomerative approach

and the divisive approach. The agglomerative approach, starts with each

object as a single cluster, and then repeatedly merge the two closest clusters

until all clusters are merged in one cluster or a termination condition holds.the point that each object is in one cluster, or until a termination

condition holds. CURE and BIRCH are two well-known hierarchical

clustering algorithms.