40 likes | 156 Views
E. 6. C. D. F. 5. 6. A. B. 1. 5. 2. 4. 5. 1. 8. c 3. 1. c 1. c 2. 2. 4. 5. 1. 8. ( 1/4). K- m eans example. Buffer. New centroid properties are needed : ” Weight ” and ” location ”.
E N D
E 6 C D F 5 6 A B 1 5 2 4 5 1 8 c3 1 c1 c2 2 4 5 1 8 (1/4) K-means example Buffer New centroidpropertiesareneeded: ”Weight” and ”location” Eachdatavectordiscardedfrombufferwillincreaseit’slastpartitioncentroid’s ’weight’ Buffer The more the centroidweights, the moreitrequirepulling to move
c3 E E c3 F C c2 c2 F D C D c1 c1 6 6 A A B B 5 5 1 1 2 2 4 4 5 5 1 1 8 8 (2/4) K-means example Buffer Buffer
6 5 c3 c3 6 1 c2 c2 5 2 1 4 5 8 c1 c1 1 2 4 5 1 8 (3/4) K-means example Starts to pull the ”heavy” Weightedcentroid! Buffer Buffer
E c3 c2 F C D c1 6 A B 5 1 2 4 5 1 8 (4/4) K-means example Buffer