Bisecting K-means There are a number of different ways to choose which cluster to split We can choose the largest cluster at each step We can also choose the one with the largest SSE We can also use a criterion based on both size and sse Different choices result in different clusters We often refine the resulting clusters by using their centroids as the initial centroids for the basic k-means algorithm The bisecting k-means algorithm is illustrated in the following figure 8/20/2016 PATTERN RECOGNITIONBisecting K-means There are a number of different ways to choose which cluster to split. ◦ We can choose the largest cluster at each step. ◦ We can also choose the one with the largest SSE. ◦ We can also use a criterion based on both size and SSE. Different choices result in different clusters. We often refine the resulting clusters by using their centroids as the initial centroids for the basic K-means algorithm. The bisecting K-means algorithm is illustrated in the following figure. 8/20/2016 PATTERN RECOGNITION 34