Documentation / Developer's manual
Available modules
Calibration,  DataServer,  Launcher,  MetaModelOptim,  Modeler,  Optimizer,  ReLauncher,  Reliability,  ReOptimizer,  Sampler,  Sensitivity,  UncertModeler,  XmlProblem,  
Uranie / Modeler v4.9.0
|
TGPCostFunction.h
Go to the documentation of this file.
Interface de la classe URANIE::Modeler::TGPBuilder.
Description of the class TGPCostFunction.
Definition TGPCostFunction.h:58
Double_t * _H
pointer to the deterministic trend matrix (size: _n * _p)
Definition TGPCostFunction.h:62
Double_t * getObservationVector()
Return a pointer to the observations outputs.
Definition TGPCostFunction.h:114
Int_t _p
number of deterministic trend coefficients
Definition TGPCostFunction.h:67
Double_t * _K
pointer to the covariance matrix (size: _n * _n)
Definition TGPCostFunction.h:63
void setBuilder(TGPBuilder *gpb)
Definition TGPCostFunction.h:125
Bool_t _blog
Boolean to decide if the log information is shown or not.
Definition TGPCostFunction.h:70
TGPBuilder * gpBuilder
pointer to a gaussian process builder object.
Definition TGPCostFunction.h:71
Double_t * getCorrelationMatrix()
Return a pointer to the GP Builder correlation matrix.
Definition TGPCostFunction.h:108
TGPBuilder * getBuilder()
Return a pointer to the GP Builder.
Definition TGPCostFunction.h:96
Int_t getNObs()
Return the number of observations.
Definition TGPCostFunction.h:120
Double_t * getCovarianceMatrix()
Return a pointer to the GP Builder covariance matrix.
Definition TGPCostFunction.h:102
Double_t * _yObs
pointer to the vector of observations outputs (size: _n)
Definition TGPCostFunction.h:65
virtual Int_t eval(Double_t *theta, Double_t *res, int=0)=0
Evaluate the cost function (implemented in the children classes)
virtual void printLog(Option_t *option="")
TGPCostFunction(TGPBuilder *gpb)
Standard constructor.
Double_t * _C
pointer to the correlation matrix (size: _n * _n)
Definition TGPCostFunction.h:64