Darwin  1.10(beta)
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Groups Pages
Public Member Functions | Protected Attributes | List of all members
drwnConditionalGaussian Class Reference

Utility class for generating conditonal gaussian distribution. More...

Inheritance diagram for drwnConditionalGaussian:
drwnStdObjIface drwnWriteable drwnCloneable drwnTypeable

Public Member Functions

 drwnConditionalGaussian (const VectorXd &mu, const MatrixXd &Sigma, const MatrixXd &SigmaGain)
 construct a conditional gaussian object with given mean, covariance and gain matrix
 
 drwnConditionalGaussian (const drwnConditionalGaussian &model)
 copy constructor
 
const char * type () const
 returns object type as a string (e.g., Foo::type() { return "Foo"; })
 
drwnConditionalGaussianclone () const
 returns a copy of the class usually implemented as virtual Foo* clone() { return new Foo(*this); }
 
bool save (drwnXMLNode &xml) const
 write object to XML node (see also write)
 
bool load (drwnXMLNode &xml)
 read object from XML node (see also read)
 
drwnGaussian reduce (const VectorXd &x)
 construct a gaussian conditioned on obeserving x
 
drwnGaussian reduce (const vector< double > &x)
 construct a gaussian conditioned on obeserving x
 
- Public Member Functions inherited from drwnWriteable
bool write (const char *filename) const
 write object to file (calls save)
 
bool read (const char *filename)
 read object from file (calls load)
 
void dump () const
 print object's current state to standard output (for debugging)
 

Protected Attributes

int _n
 dimensionality of unobserved features
 
int _m
 dimensionality of observed features (i.e., those conditioned on)
 
VectorXd _mu
 n element mean vector $ \mu_1 - \Sigma_{12} \Sigma_{22}^{-1} \mu_2 $
 
MatrixXd _mSigma
 n-by-n element covariance matrix $ \Sigma_{11} - \Sigma_{12} \Sigma_{22}^{-1} \Sigma_{21} $
 
MatrixXd _mSigmaGain
 m-by-n gain matrix $ \Sigma_{12} \Sigma_{22}^{-1} $
 

Detailed Description

Utility class for generating conditonal gaussian distribution.

The conditional gaussian is given by

\[ {\cal N}(X, Y; \mu, \Sigma \mid Y = y) = {\cal N}(X; \mu_X - \Sigma_{XY} \Sigma_{YY}^{-1} (y - \mu_Y), \Sigma_{XX} - \Sigma_{XY} \Sigma_{YY}^{-1} \Sigma_{YX}) \]

See Also
drwnGaussian, drwnML Tutorial

The documentation for this class was generated from the following files: