This class can be used to implement recurrent neural networks, or recurrent forms of other supervised models. More...

#include <GSystemLearner.h>

Inheritance diagram for GClasses::GRecurrentModel:

Public Member Functions
	GRecurrentModel (GSupervisedLearner pTransition, GSupervisedLearner pObservation, size_t actionDims, size_t contextDims, size_t obsDims, GRand pRand, std::vector< size_t > pParamDims=NULL)
	Takes ownership of pTransition and pObservation. More...

	GRecurrentModel (GDomNode pNode, GRand pRand)
	Load from a DOM. More...

virtual	~GRecurrentModel ()

virtual void	calibrate (const double *pObs)
	See the comment for GSystemLearner::calibrate. More...

double *	context ()
	Returns a pointer to the context vector. More...

size_t	contextDims ()
	Returns the number of dimensions in the context (state) vector. More...

virtual void	doAction (const double *pAction)
	See the comment for GSystemLearner::doAction. More...

GImage *	frames (GMatrix pDataAction, GMatrix pDataObs, bool calibrateContext, unsigned int frameWidth, int stepsPerImage, double scalePredictions)
	Generates a film-strip-like sequence of frames that compare the expected observations (left) with predicted observations (right). If the predictions are not in the form of images, or they are not parameterized with two variables, then this method will throw. More...

size_t	obsDims ()
	Returns the number of obs dims. More...

GSupervisedLearner *	observationFunc ()
	Returns the observation function. More...

virtual void	onFinishedComputingStateEstimate (GMatrix *pStateEstimate)
	This method is called when trainMoses finishes computing the state estimate. By default, it does nothing, but you can overload it if you wish to do something with it. More...

virtual void	onObtainValidationScore (size_t timeSlice, double seconds, double squaredError)
	If validateDuringTraining was called, then this method is called whenever validation data is obtained. More...

size_t	paramDims ()
	Trains with the back-prop-through-time algorithm. Returns the final sequence length. More...

size_t *	paramRanges ()

double *	params ()

virtual void	predict (double *pObs)
	See the comment for GSystemLearner::predict. More...

void	predictPixel (const double pParams, double pObs)

double	quickValidate (GMatrix pDataAction, GMatrix pDataObs, size_t pixelSamples, double *paramArray, bool monotonic)
	Quickly compute an error estimate for use as an optimization heurisitic. More...

virtual GDomNode *	serialize (GDom *pDoc) const
	See the comment for GSystemLearner::serialize. More...

void	setTrainingSeconds (double d)
	Set the number of seconds to train. More...

void	setUseIsomap (bool b)
	Specify whether to use Isomap (instead of BreadthFirstUnfolding). (This only applies when trainMoses is called.) More...

void	trainEvolutionary (GMatrix pActions, GMatrix pObservations)
	Trains with an evolutionary optimizer. More...

void	trainHillClimber (GMatrix pActions, GMatrix pObservations, double dev, double decay, double seconds, bool climb, bool anneal)
	Trains with a hill climber. More...

void	trainMoses (GMatrix pActions, GMatrix pObservations)
	Trains with the MOSES algorithm. (Calls onFinishedComputingStateEstimate when the state estimate is computed.) More...

GSupervisedLearner *	transitionFunc ()
	Returns the transition function. More...

double	validate (std::vector< GMatrix * > &validationData, bool calibrateContext, bool monotonic, double multiplier)
	Computes the mean squared error with respect to some test sequence of actions and observations. More...

void	validateDuringTraining (double timeInterval, std::vector< GMatrix * > *pValidationData)
	Perform validation at periodic intervals with the specified data during training. Results are passed to the onObtainValidationScore method. pValidationData should refer to some number of validation data pairs, where each validation data pair is an observation dataset followed by an action dataset. More...

Public Member Functions inherited from GClasses::GSystemLearner
	GSystemLearner ()

	GSystemLearner (GDomNode *pNode)

virtual	~GSystemLearner ()

Static Public Member Functions
static void	blurImageVector (const double pIn, double pOut, int wid, int hgt, int chan, double valueRange, int radius, int iters)
	Blur the image vector. More...

Protected Member Functions
GMatrix *	joshuaEstimateState (GMatrix pActions, GMatrix pObservations)

GMatrix *	mosesEstimateState (GMatrix pActions, GMatrix pObservations)

void	prepareForOptimization (GMatrix pActions, GMatrix pObservations)

void	trainObservationFunction (GMatrix pEstState, GMatrix pObservations)

void	trainObservationFunctionIteratively (double dStart, GMatrix pEstState, GMatrix pObservations)

void	trainTransitionFunction (GMatrix pActions, GMatrix pEstState)

Protected Member Functions inherited from GClasses::GSystemLearner
GDomNode *	baseDomNode (GDom pDoc, const char szClassName) const
	Child classes should use this in their implementation of serialize. More...

Protected Attributes
size_t	m_actionDims

size_t	m_channels

size_t	m_contextDims

double	m_multiplier

size_t	m_obsDims

size_t	m_paramDims

double *	m_pBuf

double *	m_pContext

size_t	m_pixels

GSupervisedLearner *	m_pObservationFunc

size_t *	m_pParamRanges

double *	m_pParams

GRand *	m_pRand

GSupervisedLearner *	m_pTransitionFunc

std::vector< GMatrix * > *	m_pValidationData

double	m_trainingSeconds

bool	m_transitionDelta

bool	m_useIsomap

double	m_validationInterval

Detailed Description

This class can be used to implement recurrent neural networks, or recurrent forms of other supervised models.

Constructor & Destructor Documentation

GClasses::GRecurrentModel::GRecurrentModel	(	GSupervisedLearner *	pTransition,
		GSupervisedLearner *	pObservation,
		size_t	actionDims,
		size_t	contextDims,
		size_t	obsDims,
		GRand *	pRand,
		std::vector< size_t > *	pParamDims = `NULL`
	)

Takes ownership of pTransition and pObservation.

GClasses::GRecurrentModel::GRecurrentModel	(	GDomNode *	pNode,
		GRand *	pRand
	)

Load from a DOM.

virtual GClasses::GRecurrentModel::~GRecurrentModel ( )

virtual

Member Function Documentation

static void GClasses::GRecurrentModel::blurImageVector	(	const double *	pIn,
		double *	pOut,
		int	wid,
		int	hgt,
		int	chan,
		double	valueRange,
		int	radius,
		int	iters
	)

static

Blur the image vector.

virtual void GClasses::GRecurrentModel::calibrate ( const double * pObs )

virtual

See the comment for GSystemLearner::calibrate.

Implements GClasses::GSystemLearner.

double* GClasses::GRecurrentModel::context ( )

inline

Returns a pointer to the context vector.

size_t GClasses::GRecurrentModel::contextDims ( )

inline

Returns the number of dimensions in the context (state) vector.

virtual void GClasses::GRecurrentModel::doAction ( const double * pAction )

virtual

See the comment for GSystemLearner::doAction.

Implements GClasses::GSystemLearner.

GImage* GClasses::GRecurrentModel::frames	(	GMatrix *	pDataAction,
		GMatrix *	pDataObs,
		bool	calibrateContext,
		unsigned int	frameWidth,
		int	stepsPerImage,
		double	scalePredictions
	)

Generates a film-strip-like sequence of frames that compare the expected observations (left) with predicted observations (right). If the predictions are not in the form of images, or they are not parameterized with two variables, then this method will throw.

GMatrix* GClasses::GRecurrentModel::joshuaEstimateState	(	GMatrix *	pActions,
		GMatrix *	pObservations
	)

protected

GMatrix* GClasses::GRecurrentModel::mosesEstimateState	(	GMatrix *	pActions,
		GMatrix *	pObservations
	)

protected

size_t GClasses::GRecurrentModel::obsDims ( )

inline

Returns the number of obs dims.

GSupervisedLearner* GClasses::GRecurrentModel::observationFunc ( )

inline

Returns the observation function.

virtual void GClasses::GRecurrentModel::onFinishedComputingStateEstimate ( GMatrix * pStateEstimate )

inlinevirtual

This method is called when trainMoses finishes computing the state estimate. By default, it does nothing, but you can overload it if you wish to do something with it.

Reimplemented in GClasses::MyRecurrentModel.

virtual void GClasses::GRecurrentModel::onObtainValidationScore	(	size_t	timeSlice,
		double	seconds,
		double	squaredError
	)

inlinevirtual

If validateDuringTraining was called, then this method is called whenever validation data is obtained.

size_t GClasses::GRecurrentModel::paramDims ( )

inline

Trains with the back-prop-through-time algorithm. Returns the final sequence length.

size_t* GClasses::GRecurrentModel::paramRanges ( )

inline

double* GClasses::GRecurrentModel::params ( )

inline

virtual void GClasses::GRecurrentModel::predict ( double * pObs )

virtual

See the comment for GSystemLearner::predict.

Implements GClasses::GSystemLearner.

void GClasses::GRecurrentModel::predictPixel	(	const double *	pParams,
		double *	pObs
	)

void GClasses::GRecurrentModel::prepareForOptimization	(	GMatrix *	pActions,
		GMatrix *	pObservations
	)

protected

double GClasses::GRecurrentModel::quickValidate	(	GMatrix *	pDataAction,
		GMatrix *	pDataObs,
		size_t	pixelSamples,
		double *	paramArray,
		bool	monotonic
	)

Quickly compute an error estimate for use as an optimization heurisitic.

virtual GDomNode* GClasses::GRecurrentModel::serialize ( GDom * pDoc ) const

virtual

See the comment for GSystemLearner::serialize.

void GClasses::GRecurrentModel::setTrainingSeconds ( double d )

inline

Set the number of seconds to train.

void GClasses::GRecurrentModel::setUseIsomap ( bool b )

inline

Specify whether to use Isomap (instead of BreadthFirstUnfolding). (This only applies when trainMoses is called.)

void GClasses::GRecurrentModel::trainEvolutionary	(	GMatrix *	pActions,
		GMatrix *	pObservations
	)

Trains with an evolutionary optimizer.

void GClasses::GRecurrentModel::trainHillClimber	(	GMatrix *	pActions,
		GMatrix *	pObservations,
		double	dev,
		double	decay,
		double	seconds,
		bool	climb,
		bool	anneal
	)

Trains with a hill climber.

void GClasses::GRecurrentModel::trainMoses	(	GMatrix *	pActions,
		GMatrix *	pObservations
	)

Trains with the MOSES algorithm. (Calls onFinishedComputingStateEstimate when the state estimate is computed.)

void GClasses::GRecurrentModel::trainObservationFunction	(	GMatrix *	pEstState,
		GMatrix *	pObservations
	)

protected

void GClasses::GRecurrentModel::trainObservationFunctionIteratively	(	double	dStart,
		GMatrix *	pEstState,
		GMatrix *	pObservations
	)

protected

void GClasses::GRecurrentModel::trainTransitionFunction	(	GMatrix *	pActions,
		GMatrix *	pEstState
	)

protected

GSupervisedLearner* GClasses::GRecurrentModel::transitionFunc ( )

inline

Returns the transition function.

double GClasses::GRecurrentModel::validate	(	std::vector< GMatrix * > &	validationData,
		bool	calibrateContext,
		bool	monotonic,
		double	multiplier
	)

Computes the mean squared error with respect to some test sequence of actions and observations.

void GClasses::GRecurrentModel::validateDuringTraining	(	double	timeInterval,
		std::vector< GMatrix * > *	pValidationData
	)

Perform validation at periodic intervals with the specified data during training. Results are passed to the onObtainValidationScore method. pValidationData should refer to some number of validation data pairs, where each validation data pair is an observation dataset followed by an action dataset.

Member Data Documentation

size_t GClasses::GRecurrentModel::m_actionDims

protected

size_t GClasses::GRecurrentModel::m_channels

protected

size_t GClasses::GRecurrentModel::m_contextDims

protected

double GClasses::GRecurrentModel::m_multiplier

protected

size_t GClasses::GRecurrentModel::m_obsDims

protected

size_t GClasses::GRecurrentModel::m_paramDims

protected

double* GClasses::GRecurrentModel::m_pBuf

protected

double* GClasses::GRecurrentModel::m_pContext

protected

size_t GClasses::GRecurrentModel::m_pixels

protected

GSupervisedLearner* GClasses::GRecurrentModel::m_pObservationFunc

protected

size_t* GClasses::GRecurrentModel::m_pParamRanges

protected

double* GClasses::GRecurrentModel::m_pParams

protected

GRand* GClasses::GRecurrentModel::m_pRand

protected

GSupervisedLearner* GClasses::GRecurrentModel::m_pTransitionFunc

protected

std::vector<GMatrix*>* GClasses::GRecurrentModel::m_pValidationData

protected

double GClasses::GRecurrentModel::m_trainingSeconds

protected

bool GClasses::GRecurrentModel::m_transitionDelta

protected

bool GClasses::GRecurrentModel::m_useIsomap

protected

double GClasses::GRecurrentModel::m_validationInterval

protected

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation