August 2018
Intermediate to advanced
522 pages
12h 45m
English
Another online algorithm is Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH). The structure is a little more complex, but it's fundamentally based on a tree structure called the Clustering-Feature Tree (CF-Tree), sometimes also called the Characteristic-Feature Tree. In particular, let's suppose we have a dataset, X:

A CF-Tree at level k is a tuple containing the following:

The first element is the number of samples belonging to the sub-cluster, while the remaining two are the sum of the points and the square sum of ...
Read now
Unlock full access