OpenANN::Learner Class Reference

Common base class of all learning algorithms. More...

#include <Learner.h>

Inheritance diagram for OpenANN::Learner:

Public Member Functions
	Learner ()
virtual	~Learner ()
virtual Eigen::VectorXd	operator() (const Eigen::VectorXd &x)=0
	Make a prediction. More...
virtual Eigen::MatrixXd	operator() (const Eigen::MatrixXd &X)=0
	Make predictions. More...
virtual Learner &	trainingSet (Eigen::MatrixXd &input, Eigen::MatrixXd &output)
	Set training set. More...
virtual Learner &	trainingSet (DataSet &trainingSet)
	Set training set. More...
virtual Learner &	removeTrainingSet ()
	Remove the training set from the learner. More...
virtual Learner &	validationSet (Eigen::MatrixXd &input, Eigen::MatrixXd &output)
	Set validation set. More...
virtual Learner &	validationSet (DataSet &validationSet)
	Set validation set. More...
virtual Learner &	removeValidationSet ()
	Remove the validation set from the learner. More...
Public Member Functions inherited from OpenANN::Optimizable
virtual	~Optimizable ()
virtual void	finishedIteration ()
	This callback is called after each optimization algorithm iteration. More...
virtual bool	providesInitialization ()=0
	Check if the object knows how to initialize its parameters. More...
virtual void	initialize ()=0
	Initialize the optimizable parameters. More...
virtual unsigned	dimension ()=0
	Request the number of optimizable parameters. More...
virtual const Eigen::VectorXd &	currentParameters ()=0
	Request the current parameters. More...
virtual void	setParameters (const Eigen::VectorXd &parameters)=0
	Set new parameters. More...
virtual double	error ()=0
	Compute error on training set. More...
virtual bool	providesGradient ()=0
	Check if the object provides a gradient of the error function with respect to its parameters. More...
virtual Eigen::VectorXd	gradient ()=0
	Compute gradient of the error function with respect to the parameters. More...
virtual unsigned	examples ()
	Request number of training examples. More...
virtual double	error (unsigned n)
	Compute error of a given training example. More...
virtual Eigen::VectorXd	gradient (unsigned n)
	Compute gradient of a given training example. More...
virtual void	errorGradient (int n, double &value, Eigen::VectorXd &grad)
	Calculates the function value and gradient of a training example. More...
virtual void	errorGradient (double &value, Eigen::VectorXd &grad)
	Calculates the function value and gradient of all training examples. More...
virtual Eigen::VectorXd	error (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN)
	Calculates the errors of given training examples. More...
virtual Eigen::VectorXd	gradient (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN)
	Calculates the accumulated gradient of given training examples. More...
virtual void	errorGradient (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN, double &value, Eigen::VectorXd &grad)
	Calculates the accumulated gradient and error of given training examples. More...

Protected Attributes
DataSet *	trainSet
DataSet *	validSet
bool	deleteTrainSet
bool	deleteValidSet
int	N

Detailed Description

Common base class of all learning algorithms.

A learner combines a model and a training set so that an Optimizer can minimize the error function on the training set.

Constructor & Destructor Documentation

OpenANN::Learner::Learner

(

)

virtual OpenANN::Learner::~Learner ( )

virtual

Member Function Documentation

virtual Eigen::VectorXd OpenANN::Learner::operator() ( const Eigen::VectorXd &  x)

pure virtual

Make a prediction.

Parameters

x	Input vector.

Returns

Prediction.

Implemented in OpenANN::Net, OpenANN::RBM, OpenANN::IntrinsicPlasticity, and OpenANN::SparseAutoEncoder.

virtual Eigen::MatrixXd OpenANN::Learner::operator() ( const Eigen::MatrixXd &  X)

pure virtual

Make predictions.

Parameters

X	Each row represents an input vector.

Returns

Each row represents a prediction.

Implemented in OpenANN::Net, OpenANN::RBM, OpenANN::IntrinsicPlasticity, and OpenANN::SparseAutoEncoder.

virtual Learner& OpenANN::Learner::removeTrainingSet ( )

virtual

Remove the training set from the learner.

Returns

this for chaining

virtual Learner& OpenANN::Learner::removeValidationSet ( )

virtual

Remove the validation set from the learner.

Returns

this for chaining

virtual Learner& OpenANN::Learner::trainingSet ( Eigen::MatrixXd &  input, Eigen::MatrixXd &  output  )

virtual

Set training set.

Parameters

input	input vectors, each instance should be in a row
output	output vectors, each instance should be in a row

Returns

this for chaining

virtual Learner& OpenANN::Learner::trainingSet ( DataSet &  trainingSet)

virtual

Set training set.

Parameters

trainingSet

training set

Returns

this for chaining

Reimplemented in OpenANN::SparseAutoEncoder.

virtual Learner& OpenANN::Learner::validationSet ( Eigen::MatrixXd &  input, Eigen::MatrixXd &  output  )

virtual

Set validation set.

Parameters

input	input vectors, each instance should be in a row
output	output vectors, each instance should be in a row

Returns

this for chaining

virtual Learner& OpenANN::Learner::validationSet ( DataSet &  validationSet)

virtual

Set validation set.

Parameters

validationSet

validation set

Returns

this for chaining

Member Data Documentation

bool OpenANN::Learner::deleteTrainSet

protected

bool OpenANN::Learner::deleteValidSet

protected

int OpenANN::Learner::N

protected

DataSet* OpenANN::Learner::trainSet

protected

DataSet* OpenANN::Learner::validSet

protected

---

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

• OpenANN/Learner.h