Institut de Robòtica i Informàtica Industrial

FuseComponents

PURPOSE ^

Fuses a Gaussian mixture into a single Gaussian.

SYNOPSIS ^

function g=FuseComponents(gm)

DESCRIPTION ^

   Fuses a Gaussian mixture into a single Gaussian.

   Summarizes the information on a Gaussian mixture into a single
   Gaussian.
   The mean of the output Gaussian is the weighted mean of the components
   in the input mixture.
   The covariance is basically the weighted mean of the covariance of the
   components but it also take into account the dispersion of the mean of
   the components.

   See also @GMixture/Mean, @GMixture/Covariance, CompressGR.

CROSS-REFERENCE INFORMATION ^

This function calls:
  • get Get for GBeliefs.
  • Covariance Average covariance of a Gaussian mixture.
  • Mean Mean of a Gmixture.
  • get Get function for the GMixture object.
  • Gaussian Gaussian construtor.
  • get Gaussian object get function.
  • get Get function for CS_CO_CA_POMDPs.
  • get Get function for CS_CO_DA_POMDPs.
  • get Get function for CS_CO_POMDPs.
  • get Get function for CS_DO_CA_POMDPs.
  • get Get function for CS_DO_DA_POMDPs.
  • get Get function for CS_POMDPs.
  • get Get function for DS_CO_CA_POMDPs.
  • get Get function for DS_CO_DA_POMDPs.
  • get Get function for DS_DO_CA_POMDPs.
  • get Get function for DS_DO_DA_POMDPs.
  • get Get functio for POMDPs.
This function is called by:
  • CompressGR Gaussian mixture compression using the Golberger and Roweis method.

SOURCE CODE ^

0001 function g=FuseComponents(gm)
0002 %   Fuses a Gaussian mixture into a single Gaussian.
0003 %
0004 %   Summarizes the information on a Gaussian mixture into a single
0005 %   Gaussian.
0006 %   The mean of the output Gaussian is the weighted mean of the components
0007 %   in the input mixture.
0008 %   The covariance is basically the weighted mean of the covariance of the
0009 %   components but it also take into account the dispersion of the mean of
0010 %   the components.
0011 %
0012 %   See also @GMixture/Mean, @GMixture/Covariance, CompressGR.
0013   m=Mean(gm);
0014   S=Covariance(gm);
0015   for i=1:gm.n
0016     v=(get(gm.g{i},'mean')-m);
0017     S=S+gm.w(i)*(v*v');
0018   end
0019   g=Gaussian(m,S);
0020


Institut de Robòtica i Informàtica Industrial

Generated on Wed 05-Aug-2009 15:05:21 by m2html © 2003