Skip to Main Content
Building an Intelligent Web: Theory and Practice
book

Building an Intelligent Web: Theory and Practice

by Pawan Lingras, Rajendra Akerkar
March 2010
Intermediate to advanced content levelIntermediate to advanced
326 pages
12h 25m
English
Jones & Bartlett Learning
Content preview from Building an Intelligent Web: Theory and Practice
“4137X˙CH05˙Akerkar” 2007/9/8 11:01 page 187 #11
5.2 Statistical Methods 187
5.2.2 Other Methods
5.2.2.1 Probabilistic Clustering
There are some differences between partition-based clustering and probabilistic clustering.
The idea for the partition-based algorithm is that if a point belongs to a cluster, it belongs
exclusively to that cluster. Probabilistic clustering, on the other hand, permits a point x to
have partial membership in a cluster.
The idea behind the partition-based algorithm does lead to some problems. In the graph
in
Figure 5.11, point x has the same distance from c
i
and c
j
, so it is unfair to let it belong
exclusively
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Reinventing the Organization for GenAI and LLMs

Reinventing the Organization for GenAI and LLMs

Ethan Mollick

Publisher Resources

ISBN: 9780763741372