Contents
What is Kmeans good for?
The K-means clustering algorithm is used to find groups which have not been explicitly labeled in the data. This can be used to confirm business assumptions about what types of groups exist or to identify unknown groups in complex data sets.
Under what conditions does EM algorithm become k-means?
1. k-means “assumes” that the clusters are more or less round and solid (not heavily elongated or curved or just ringed) clouds in euclidean space. They are not required to come from normal distributions. EM does require it (or at least specific type of distribution to be known).
Is there a similarity between k-means and Em?
There is a close similarity between k-means algorithm and EM algorithm for GMM. The first way to understand is from the two-stage update process. Both of the algorithms share an expectation stage and a maximization stage. The second way is we can derive the k-means as a particular limit EM for GMM.
What are the advantages and disadvantages of k-means?
Clustering data of varying sizes and density. k-means has trouble clustering data where clusters are of varying sizes and density. To cluster such data, you need to generalize k-means as described in the Advantages section.
Why do we need advanced versions of k-means?
As k increases, you need advanced versions of k-means to pick better values of the initial centroids (called k-means seeding ). For a full discussion of k- means seeding see, A Comparative Study of Efficient Initialization Methods for the K-Means Clustering Algorithm by M. Emre Celebi, Hassan A. Kingravi, Patricio A. Vela.
Which is the best way to derive the k-means?
The second way is we can derive the k-means as a particular limit EM for GMM. The key is to make the soft assignment to be a hard one. We can simply use a to force the probabilities to be binary, or consider a GMM setting with covariance matrix to be where .