Hello Id like to know if it's possible to train SOM in unlabelled data. As it's a clustering algorithm. My doubt is, I see people applying it in iris data set which is labelled. Is it possible so for unlabelled data?

Can clustering work for dataset with many binaries columns? for example if I've 70 columns, with 40 out pf them in (0, 1).

  • $\begingroup$ If you look at Wikipedia you will see that SOM is an unsupervised method, that is, does not use labeling. $\endgroup$ – kjetil b halvorsen May 13 at 17:48

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.