TNormalVariable.h File Reference

A TNormalVariable encapsulates MCMC operations on a single real number with a standard normal prior. This is useful for variables in e.g. GrammarInference. This has a normal prior on a parameter and then allows an output transformation, which is cached for speed. More...

#include "EigenLib.h"
#include "Interfaces/MCMCable.h"

Include dependency graph for TNormalVariable.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	TNormalVariable< f >

Typedefs
using	UniformVariable = TNormalVariable<+[](float x) ->float { return normal_cdf< float >(x, 0.0, 1.0)
using	ExponentialVariable = TNormalVariable<+[](float x) ->float { return -log(normal_cdf< float >(-x, 0.0, 1.0))

Detailed Description

A TNormalVariable encapsulates MCMC operations on a single real number with a standard normal prior. This is useful for variables in e.g. GrammarInference. This has a normal prior on a parameter and then allows an output transformation, which is cached for speed.

Typedef Documentation

ExponentialVariable

using ExponentialVariable = TNormalVariable< +[](float x)->float { return -log(normal_cdf<float>(-x, 0.0, 1.0))

UniformVariable

using UniformVariable = TNormalVariable< +[](float x)->float { return normal_cdf<float>(x, 0.0, 1.0)