I suspect that if there are many unimportant outliers, trimmed k-mean clustering should be employed.
Am I on the right track?
$\begingroup$
$\endgroup$
1
-
$\begingroup$ Yes. The original trimmed $k$-means1997 paper by Cuesta-Albertos et al. did exactly that. $\endgroup$– usεr11852May 14, 2017 at 0:28
Add a comment
|