loading…
A4.3.4 HL · unsupervised learning
k-means groups unlabelled data into k clusters. Each step assigns each point to its nearest centroid (cluster centre), then moves each centroid to the mean position of its assigned points. Change the starting centres to see whether the clusters change.
The ringed crosses are the centroids (the centre of each cluster). Each step gives every point the colour of its nearest centroid, then moves each centroid to the average position of its points. Click to add a point.