In K-clustering there are several methods like the elbow method and kernel method to find the number of k-centroids in the given cluster. However, to ascertain an approximate number of centroids quickly, we can also take the square root of the number of data points divided by two. While this technique of determining clusters in K-means is not entirely accurate, but it is faster as compared with the previously mentioned techniques.
Uh oh, we're definitely being carded. Here, show him this tiny ad:
ScroogeXHTML - small and flexible RTF to HTML converter library