Question: Consider the K-Means algorithm run on a dataset of 100 points and 10 clusters. If the number of data points is fixed but number of
Consider the K-Means algorithm run on a dataset of 100 points and 10 clusters.
If the number of data points is fixed but number of clusters (and number of initial centroids)
increases, will it improve or diminish your chance of finding the optimal k-means solution by
randomly choosing a subset of the data points to be the initial centroids?
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
