View Single Post
Old 09-17-2012, 07:00 PM
MLearning MLearning is offline
Senior Member
Join Date: Jul 2012
Posts: 56
Default Re: How Many Iterations to Pick Best K-Cluster?

Originally Posted by DavidNJ View Post
To pick the best set of K-Means clusters centroids for each training set, how many times should be generate the centroids to find the best? 10? 100? 1000? The higher number provides the higher probability of finding the the centroids with the lowest Eout.


You need a condition that stops iteration when the centroids do not change.
Reply With Quote