I have a distance matrix for some data I want to cluster. However, I don't just want to assign elements to clusters, but I also want to assign a probability for each element to belong to each cluster.

Can you give me examples of clustering algorithms that can do that?

Is there, for instance, a hierarchical clustering algorithm that returns, for each element, a probability to belong to any cluster?

  • $\begingroup$ This question is very much like your previous one. Please merge them into one question. $\endgroup$ – ttnphns Mar 13 '14 at 17:32
  • $\begingroup$ check out Naive Bayes classifiers $\endgroup$ – Eric Peterson Mar 13 '14 at 17:36

Learn about fuzzy clustering.

There is just so much more than plain old k-means...

Fuzzy algorithms assign non-binary cluster memberships, so it sounds like exactly what you are asking for. Again, this is not a single algorithm. This is a whole research subtopic.

| cite | improve this answer | |
  • $\begingroup$ I read about GraphLab bu do you recommend another library (preferably in python) for implementing fuzzy algorithms? $\endgroup$ – bigTree Mar 14 '14 at 10:19

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.