Suppose we find K clusters using Ward’s method, bisecting K-means, and ordinary K-means. Which of these solutions represents a local or global minimum? Explain.

What will be an ideal response?

Although Ward’s method picks a pair of clusters to merge based on mini-
mizing SSE, there is no refinement step as in regular K-means. Likewise,

bisecting K-means has no overall refinement step. Thus, unless such a refine-
ment step is added, neither Ward’s method nor bisecting K-means produces

a local minimum. Ordinary K-means produces a local minimum, but like the

Computer Science & Information Technology

You might also like to view...

If one customer can purchase many items, one-to-many is called the ________ of the relationship

A) joining B) redundancy C) integrity D) cardinality

Computer Science & Information Technology

The ________ data type is used to hold sentences or paragraphs of descriptive data

A) OLE B) Text C) Hyperlink D) Memo

Computer Science & Information Technology