Mira::Optimiser Class Reference

#include <Optimiser.h>

Inheritance diagram for Mira::Optimiser:

[legend]

List of all members.

Public Member Functions
	Optimiser ()
virtual size_t	updateWeightsHopeFear (Moses::ScoreComponentCollection &weightUpdate, const std::vector< std::vector< Moses::ScoreComponentCollection > > &featureValuesHope, const std::vector< std::vector< Moses::ScoreComponentCollection > > &featureValuesFear, const std::vector< std::vector< float > > &bleuScoresHope, const std::vector< std::vector< float > > &bleuScoresFear, const std::vector< std::vector< float > > &modelScoresHope, const std::vector< std::vector< float > > &modelScoresFear, float learning_rate, size_t rank, size_t epoch, int updatePosition=-1)=0

---

Detailed Description

Definition at line 30 of file Optimiser.h.

---

Constructor & Destructor Documentation

Mira::Optimiser::Optimiser

(

)

[inline]

Definition at line 33 of file Optimiser.h.

---

Member Function Documentation

virtual size_t Mira::Optimiser::updateWeightsHopeFear	(	Moses::ScoreComponentCollection &	weightUpdate,
		const std::vector< std::vector< Moses::ScoreComponentCollection > > &	featureValuesHope,
		const std::vector< std::vector< Moses::ScoreComponentCollection > > &	featureValuesFear,
		const std::vector< std::vector< float > > &	bleuScoresHope,
		const std::vector< std::vector< float > > &	bleuScoresFear,
		const std::vector< std::vector< float > > &	modelScoresHope,
		const std::vector< std::vector< float > > &	modelScoresFear,
		float	learning_rate,
		size_t	rank,
		size_t	epoch,
		int	updatePosition = -1
	)			[pure virtual]

Implemented in Mira::Perceptron, and Mira::MiraOptimiser.

Referenced by main().

Here is the caller graph for this function:

---

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

• mosesdecoder/mira/Optimiser.h