EM experiment #2: red class, full covariances

Number of Gaussians, assumes full covariance matrices

Choose number of Gaussians in mixture model

Assumes full covariance matrices

Compute EM algorithm

RowBox[{Timing, [, RowBox[{RowBox[{em, , =, , RowBox[{EM, [, RowBox[{data1, ,, initFull, ,, 0.001}], ]}]}], ;}], ]}]

RowBox[{{, RowBox[{RowBox[{0.2, , Second}], ,, Null}], }}]

Visualization

Initial model

PolygonalAllPlot[poly, em//First] ;

[Graphics:../HTMLFiles/index_43.gif]

Final model

PolygonalAllPlot[poly, em // Last] ;

[Graphics:../HTMLFiles/index_45.gif]

Plot log-likelihood of data given the model as a function of EM iteration

PlotLogLikelihood[em, data1] ;

[Graphics:../HTMLFiles/index_47.gif]

Save solution

Created by Mathematica  (September 8, 2003)