lecture12-clustering-handout-6-per

In order to maintain an overall on2 performance

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: omplete ­link   Similarity of the furthest points, the least cosine ­similar   Centroid   Clusters whose centroids (centers of gravity) are the most cosine ­similar   Average ­link Note: the resulting clusters are still hard and induce a partition Introduc)on to Informa)on Retrieval Sec. 17.2 Single Link Agglomera*ve Clustering   Average cosine between pairs of elements Introduc)on to Informa)on Retrieval Sec. 17.2 Single Link Example   Use maximum similarity of pairs: sim(ci ,c j ) = max sim( x, y) x∈ci , y∈c j   Can result in straggly (long and thin) clusters due to chaining effect.   Ager merging ci and cj, the similarity of the resul*ng cluster to another cluster, ck, is: sim(( ci ∪ c j ), ck ) = max( sim(ci , ck ), sim(c j , ck )) 6 Introduc)on to Informa)on Retrieval ec. 17.2 S Complete Link Introduc)on to Informa)on Retrieval Sec. 17.2 Comp...
View Full Document

This document was uploaded on 02/26/2014.

Ask a homework question - tutors are online