On Jun 25, 2009, at 10:17 PM, Ted Dunning wrote:
Rephrasing: Option 1) pick a single (or three) random input vector as the initial position of each centroidOption 2) assign every input vector to some centroid at random and computethe resulting centroidsOption (1) is like (2), but it only assigns k input vectors while option (2) assigns all input vectors to some cluster. Many people use (2), but (1)generally works better for me.
Gotcha. Option 1 was what I had in mind.
