Gaussian
PURPOSE 
Gaussian construtor.
SYNOPSIS
function g=Gaussian(varargin)
DESCRIPTION
Gaussian construtor. Multi-dimensional Gaussian constructor. The input parameters can be another Gaussian, from a collection of points of from the mean and covariance matrix.
CROSS-REFERENCE INFORMATION
This function calls:
This function is called by:
- GetActionModelFixedA Returns the action model for a given action.
- CS_DA_ActionModel CS_DA_ActionModel constructor.
- DiscretizeActionModel Produces a new action model discretizing the state space.
- Update Belief evolution under an observation model.
- GetTest1Parameters The example on Figure 1.
- GetTest1caParameters The example on Figure 10.
- GetTest1coParameters The example on Figure 11.
- MakeFigure4 Generates Figure 4.
- FuseComponents Fuses a Gaussian mixture into a single Gaussian.
- ProductInt Product and marginalization of two GMixtures.
- Gaussian Gaussian construtor.
- Offset Adds a constant to a Gaussian.
- ProductNormFactor Normalization constant of the product of two Gaussians.
- Scale Product of a Gaussian and a constant (matrix).
- plus Adds a Gaussian and a constant/Gaussian.
- UniformDistribution Uniform probability on a continuous space.
SOURCE CODE
0001 function g=Gaussian(varargin) 0002 % Gaussian construtor. 0003 % 0004 % Multi-dimensional Gaussian constructor. The input parameters can be 0005 % another Gaussian, from a collection of points of from the mean and 0006 % covariance matrix. 0007 0008 switch nargin 0009 case 1 0010 if isa(varargin{1},'Gaussian') 0011 g=varargin{1}; 0012 else 0013 if isa(varargin{1},'double') 0014 % assuming we have to define the Gaussian from samples (arranged 0015 % in columns) 0016 n=size(varargin{1},2); % number of data 0017 m=mean(varargin{1},2); 0018 Pz=(varargin{1}-repmat(m,1,n)); % zero centered points 0019 C=(Pz*Pz')/(n-1); % unbiased covariance 0020 g=Gaussian(m,C); 0021 else 0022 error('Gaussian copy constructor from not a Guassian and not a raw data'); 0023 end 0024 end 0025 0026 case 2 0027 g.m=varargin{1}; 0028 g.dim=size(g.m,1); 0029 g.S=varargin{2}; 0030 0031 if (g.dim~=size(g.S,1)) || (g.dim~=size(g.S,2)) 0032 error('Non-coherent size of mean an covariance in Gaussian creation'); 0033 end 0034 0035 m=max(max(g.S)); 0036 if m==0 0037 g.d=0; 0038 g.iS=inf*eye(g.dim); 0039 g.ct=0; 0040 else 0041 if g.dim==1 0042 g.d=g.S; 0043 g.iS=1/g.S; 0044 g.ct=1/sqrt(2*pi*g.d); 0045 else 0046 R=chol(g.S); 0047 g.d=prod(diag(R))^2; 0048 iR=R\eye(g.dim); 0049 g.iS=iR*iR'; 0050 %The normalization factor (in multiplicative form) 0051 g.ct=1/sqrt(((2*pi)^g.dim)*g.d); 0052 end 0053 end 0054 g=class(g,'Gaussian'); 0055 otherwise 0056 error('Wrong number of parameters in Gaussian constructor'); 0057 end 0058