DataGeneratorRegression

class DataGeneratorRegression : public DataGeneratorBase

Subclassed by DataGeneratorRegression1D, DataGeneratorRegression2D, DataGeneratorRegression3D

Public Functions

DataGeneratorRegression(Config *settings)

Class constructor. Generates training data for neural network approaches using spherical harmonics and an entropy functional and the quadrature specified by the options file.

Parameters:

settings – config class with global information

virtual void ComputeTrainingData() override

computes the training data set. Realizable set is sampled uniformly. Prototype: 1D, u in [0,100]

inline VectorVector GetAlpha()

Get the computed solution vector uSol.

inline std::vector<double> GethEntropy()

Get the computed vector alpha.

Protected Functions

virtual void SampleSolutionU() = 0

Samples solution vectors u.

void ComputeEntropyH_dual()

Compute the entropy functional at (u,alpha) in dual formulation.

void ComputeEntropyH_primal()

Compute the entropy functional at (u,alpha) in primal formulation.

virtual void PrintTrainingData() override

: Print computed training data to csv file and screen

virtual void CheckRealizability() = 0

Debugging helper. Will be removed.

virtual void ComputeSetSizeU() = 0

Computes the size of the training set, depending on the chosen settings.

void ComputeSetSizeAlpha()

Computes the seSize for alphasampling.

void RotateMomentsAndMultipliers()

Rotates Moments and Multipliers to x axis.

Protected Attributes

std::vector<double> _hEntropy

Get the computed entropy value h.

vector with entropy values. Size: (setSize)

unsigned long _gridSize

Size of the grid discretizing moment U0 for higher order sampling (has different uses for different samplers)