lecture12-clustering-handout-6-per

Internal criterion a good clustering will produce high

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: lete Link Example   Use minimum similarity of pairs: sim(ci ,c j ) = min sim( x, y ) x∈ci , y∈c j   Makes *ghter, spherical clusters that are typically preferable.   Ager merging ci and cj, the similarity of the resul*ng cluster to another cluster, ck, is: sim(( ci ∪ c j ), ck ) = min( sim(ci , ck ), sim(c j , ck )) Ci Cj Introduc)on to Informa)on Retrieval Ck Sec. 17.2.1 Introduc)on to Informa)on Retrieval Sec. 17.3 Group Average Computa*onal Complexity   In the first itera*on, all HAC methods need to compute similarity of all pairs of N ini*al instances, which is O(N2).   In each of the subsequent N ­2 merging itera*ons, compute the distance between the most recently created cluster and all other exis*ng clusters.   In order to maintain an overall O(N2) performance, compu*ng similarity to each other cluster must be done in constant *me.   Similarity of two c...
View Full Document

This document was uploaded on 02/26/2014.

Ask a homework question - tutors are online