bdm Namespace Reference
[Core BDM classes]

Space of basic BDM structures. More...


Classes

class  ARX
 Linear Autoregressive model with Gaussian noise. More...
class  EKFful_unQR
 Extended Kalman filter with unknown Q and R. More...
class  EKFCh_unQ
 Extended Kalman filter in Choleski form with unknown Q. More...
class  EKFCh_cond
 Extended Kalman filter with unknown parameters in IM. More...
class  KalmanFull
 Basic Kalman filter with full matrices (education purpose only)! Will be deleted soon! More...
class  Kalman
 Kalman filter with covariance matrices in square root form. More...
class  KalmanCh
 Kalman filter in square root form. More...
class  EKFfull
 Extended Kalman Filter in full matrices. More...
class  EKF
 Extended Kalman Filter. More...
class  EKFCh
 Extended Kalman Filter in Square root. More...
class  KFcondQR
 Kalman Filter with conditional diagonal matrices R and Q. More...
class  KFcondR
 Kalman Filter with conditional diagonal matrices R and Q. More...
class  PF
 Trivial particle filter with proposal density equal to parameter evolution model. More...
class  MPF
 Marginalized Particle filter. More...
class  merger
 Function for general combination of pdfs. More...
class  MixEF
 Mixture of Exponential Family Densities. More...
class  mratio
 Class representing ratio of two densities which arise e.g. by applying the Bayes rule. It represents density in the form:

\[ f(rv|rvc) = \frac{f(rv,rvc)}{f(rvc)} \]

where $ f(rvc) = \int f(rv,rvc) d\ rv $. More...

class  emix
 Mixture of epdfs. More...
class  mprod
 Chain rule decomposition of epdf. More...
class  eprod
 Product of independent epdfs. For dependent pdfs, use mprod. More...
class  mmix
 Mixture of mpdfs with constant weights, all mpdfs are of equal type. More...
class  bdmroot
 Root class of BDM objects. More...
class  str
 Structure of RV (used internally), i.e. expanded RVs. More...
class  RV
 Class representing variables, most often random variables. More...
class  fnc
 Class representing function $f(x)$ of variable $x$ represented by rv. More...
class  epdf
 Probability density function with numerical statistics, e.g. posterior density. More...
class  mpdf
 Conditional probability density, e.g. modeling some dependencies. More...
class  datalink_e2e
 DataLink is a connection between two data vectors Up and Down. More...
class  datalink_m2e
 data link between More...
class  datalink_m2m
class  mepdf
 Unconditional mpdf, allows using epdf in the role of mpdf. More...
class  compositepdf
 Abstract composition of pdfs, will be used for specific classes this abstract class is common to epdf and mpdf. More...
class  DS
 Abstract class for discrete-time sources of data. More...
class  BM
 Bayesian Model of the world, i.e. all uncertainty is modeled by probabilities. More...
class  BMcond
 Conditional Bayesian Filter. More...
class  MemDS
 Memory storage of off-line data column-wise. More...
class  ArxDS
 Generator of ARX data. More...
class  eEF
 General conjugate exponential family posterior density. More...
class  mEF
 Exponential family model. More...
class  BMEF
 Estimator for Exponential family. More...
class  enorm
 Gaussian density with positive definite (decomposed) covariance matrix. More...
class  egiw
 Gauss-inverse-Wishart density stored in LD form. More...
class  eDirich
 Dirichlet posterior density. More...
class  multiBM
 Estimator for Multinomial density. More...
class  egamma
 Gamma posterior density. More...
class  eigamma
 Inverse-Gamma posterior density. More...
class  euni
 Uniform distributed density on a rectangular support. More...
class  mlnorm
 Normal distributed linear function with linear function of mean value;. More...
class  mlstudent
class  mgamma
 Gamma random walk. More...
class  migamma
 Inverse-Gamma random walk. More...
class  mgamma_fix
 Gamma random walk around a fixed point. More...
class  migamma_fix
 Inverse-Gamma random walk around a fixed point. More...
class  eEmp
 Weighted empirical density. More...
class  constfn
 class representing function $f(x) = a$, here rv is empty More...
class  linfn
 Class representing function $f(x) = Ax+B$. More...
class  diffbifn
 Class representing a differentiable function of two variables $f(x,u)$. More...
class  bilinfn
 Class representing function $f(x,u) = Ax+Bu$. More...
class  logger
 Class for storing results (and semi-results) of an experiment. More...
class  memlog
 Logging into matrices in data format in memory. More...
class  dirfilelog
 Logging into dirfile with buffer in memory. More...
class  UIFile
class  UIbuilder
 Builds computational object from a UserInfo structure. More...
class  UIexternal
class  UIinternal

Typedefs

typedef map< const string,
const UIbuilder * > 
UImap
 Internal structure mapping strings to UIBuilder objects.

Enumerations

enum  MixEF_METHOD { EM = 0, QB = 1 }
enum  RESAMPLING_METHOD { MULTINOMIAL = 0, STRATIFIED = 1, SYSTEMATIC = 3 }
 Switch between various resampling methods.

Functions

double egiw_bestbelow (egiw Eg, egiw Eg0, double Egll, ivec &indeces)
 Return the best structure.
std::ostream & operator<< (std::ostream &os, const KalmanFull &kf)
std::ostream & operator<< (std::ostream &os, const RV &rv)
RV concat (const RV &rv1, const RV &rv2)
 Concat two random variables.
template<class sq_T>
std::ostream & operator<< (std::ostream &os, mlnorm< sq_T > &ml)
 UIREGISTER (UIexternal)
 UIREGISTER (UIinternal)
void UI_DBG (Setting &S, const string &spc)
 [Debugging] Print values in current S to cout
template<class T>
void UIbuild (Setting &S, T *&ret)
 Prototype of a UI builder. Return value is by the second argument since it type checking via dynamic_cast.
template<class T>
void UIcall (Setting &S, void(*func)(Setting &, T), T Tmp)
 Auxiliary function allowing recursivity in S (too complex, remove?).

Variables

RV RV0 = RV()
 Default empty RV that can be used as default argument.
Uniform_RNG UniRNG
 Global Uniform_RNG.
Normal_RNG NorRNG
 Global Normal_RNG.
Gamma_RNG GamRNG
 Global Gamma_RNG.
UImap __uimap__
 global map of UIbulder names to instances of UIbuilders. Created by UIREGISTER macro


Detailed Description

Space of basic BDM structures.

Function Documentation

double bdm::egiw_bestbelow ( egiw  Eg,
egiw  Eg0,
double  Egll,
ivec &  indeces 
)

Return the best structure.

Parameters:
Eg a copy of GiW density that is being examined
Eg0 a copy of prior GiW density before estimation
Egll likelihood of the current Eg
indeces current indeces
Returns:
best likelihood in the structure below the given one

References ldmat::_D(), ldmat::_L(), bdm::egiw::_V(), ldmat::ldform(), bdm::egiw::lognc(), and ldmat::rows().

Referenced by bdm::ARX::structure_est().


Generated on Fri Feb 6 15:29:50 2009 for mixpp by  doxygen 1.5.6