sebastian-schindler / PhD

0 stars 0 forks source link

Test clustering algorithm with toy clusters in real data #4

Open sebastian-schindler opened 6 months ago

sebastian-schindler commented 6 months ago

Introducing artificial into existing data allows to test a clustering algorithm's performance, and judge which area of the hyperparameter space is relevant. If a cluster algorithm cannot distinguish an obvious cluster at all, or only with a certain set of hyperparameters, this tells us whether the algorithm is useful at all, or with which hyperparameter configuration it is.

These toy clusters can be introduced...

Systematic testing can be done by making it successively harder to distinguish the toy cluster: