| SOM Toolbox | Online documentation | http://www.cis.hut.fi/projects/somtoolbox/ |
[pd,Pdm,pmd] = som_probability_gmm(D, sM, K, P)
SOM_PROBABILITY_GMM Probabilities based on a gaussian mixture model.
[pd,Pdm,pmd] = som_probability_gmm(D, sM, K, P)
[K,P] = som_estimate_gmm(sM,D);
[pd,Pdm,pmd] = som_probability_gmm(D,sM,K,P);
som_show(sM,'color',pmd(:,1),'color',Pdm(:,1))
Input and output arguments:
D (matrix) size dlen x dim, the data for which the
(struct) data struct, probabilities are calculated
sM (struct) map struct
(matrix) size munits x dim, the kernel centers
K (matrix) size munits x dim, kernel width parameters
computed by SOM_ESTIMATE_GMM
P (matrix) size 1 x munits, a priori probabilities for each
kernel computed by SOM_ESTIMATE_GMM
pd (vector) size dlen x 1, probability of each data vector in
terms of the whole gaussian mixture model
Pdm (matrix) size munits x dlen, probability of each vector in
terms of each kernel
pmd (matrix) size munits x dlen, probability of each vector to
have been generated by each kernel
See also SOM_ESTIMATE_GMM.