Back-Propagation Algorithm implementation. More...

Inheritance diagram for BackPropagationAlgo:

Public Member Functions
	BackPropagationAlgo (NeuralNet *n_n, UpdatableList update_order, double l_r=0.1)
	Constructor. More...

	BackPropagationAlgo ()
	Default Constructor. More...

	~BackPropagationAlgo ()
	Destructor. More...

virtual double	calculateMSE (const Pattern &)
	Calculate the Mean Square Error respect to Pattern passed. More...

virtual void	configure (ConfigurationParameters &params, QString prefix)
	Configures the object using a ConfigurationParameters object. More...

void	disableMomentum ()
	Disable momentum. More...

void	enableMomentum ()
	Enable the momentum. More...

DoubleVector	getError (Cluster *)
	This method returns the deltas calculated by the Back-propagation Algorithm. More...

virtual void	learn ()
	a single step of learning algorithm More...

virtual void	learn (const Pattern &)
	Starts a single training step. More...

double	momentum () const
	return the momentum More...

double	rate () const
	return the learning rate More...

virtual void	save (ConfigurationParameters &params, QString prefix)
	Save the actual status of parameters into the ConfigurationParameters object passed. More...

void	setMomentum (double newmom)
	Set the momentum value. More...

void	setRate (double newrate)
	Set the learning rate. More...

void	setTeachingInput (Cluster *output, const DoubleVector &ti)
	Set the teaching input for Cluster passed. More...

void	setUpdateOrder (const UpdatableList &update_order)
	Set the order on which the error is backpropagated through the NeuralNet. More...

UpdatableList	updateOrder () const
	Return the order on which the error is backpropaget through the NeuralNet. More...

Public Member Functions inherited from LearningAlgorithm
	LearningAlgorithm (NeuralNet *net)
	Constructor. More...

	LearningAlgorithm ()
	Constructor. More...

virtual	~LearningAlgorithm ()
	Destructor. More...

virtual double	calculateMSEOnSet (const PatternSet &set)
	Calculate the Mean Square Error respect to all Patterns passed. More...

double	calculateRMSD (const Pattern &p)
	Calculate the Root Mean Square Deviation, i.e. More...

double	calculateRMSDOnSet (const PatternSet &p)
	Calculate the Root Mean Square Deviation, i.e. More...

virtual void	learnOnSet (const PatternSet &set)
	Modify the object tring to learn all patterns present into PatternSet passed. More...

PatternSet	loadPatternSet (ConfigurationParameters &params, QString path, QString prefix)
	Utility function for loading a PatternSet from a ConfigurationParameters. More...

NeuralNet *	neuralNet ()
	Return the NeuralNet setted. More...

void	savePatternSet (PatternSet &set, ConfigurationParameters &params, QString prefix)
	Utility function for saving a PatternSet to a ConfigurationParameters. More...

void	setNeuralNet (NeuralNet *net)
	Set the NeuralNet to learn. More...

Public Member Functions inherited from ParameterSettable
void	addObserver (RuntimeParameterObserver *obs)

T	getRuntimeParameter (QString paramName)

virtual ParameterSettableUI *	getUIManager ()

virtual void	postConfigureInitialization ()

void	removeObserver (RuntimeParameterObserver *obs)

void	setRuntimeParameter (QString paramName, T newvalue)

QString	typeName () const

Static Public Member Functions
static void	describe (QString type)
	Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups. More...

Static Public Member Functions inherited from ParameterSettable
static void	describe (QString type)

static QString	fullParameterDescriptionPath (QString type, QString param)

static QString	fullSubgroupDescriptionPath (QString type, QString sub)

Protected Member Functions
virtual void	neuralNetChanged ()
	Configure internal data for backpropagation on NeuralNet setted. More...

Protected Member Functions inherited from ParameterSettable
void	notifyChangesToParam (QString paramName)

Additional Inherited Members
Public Types inherited from ParameterSettable
enum	Property

Public Attributes inherited from ParameterSettable
	AllowMultiple

	Default

	IsList

	IsMandatory

Static Public Attributes inherited from ParameterSettable
static const double	Infinity

static const int	MaxInteger

static const int	MinInteger

Static Protected Member Functions inherited from ParameterSettable
static Descriptor	addTypeDescription (QString type, QString shortHelp, QString longHelp=QString(""))

static void	setGraphicalEditor (QString type)

Detailed Description

Back-Propagation Algorithm implementation.

Definition at line 35 of file backpropagationalgo.h.

Constructor & Destructor Documentation

BackPropagationAlgo	(	NeuralNet *	n_n,
		UpdatableList	update_order,
		double	l_r = `0.1`
	)

Constructor.

Parameters

neural_network	the BaseNeuralNet neural network to train
update_order	the UpdatableList for the backpropagation sequence
learn_rate	the double learning rate factor

Definition at line 27 of file backpropagationalgo.cpp.

References BackPropagationAlgo::neuralNetChanged().

BackPropagationAlgo ( )

Default Constructor.

Definition at line 34 of file backpropagationalgo.cpp.

References BackPropagationAlgo::neuralNetChanged().

~BackPropagationAlgo ( )

Destructor.

Definition at line 41 of file backpropagationalgo.cpp.

Member Function Documentation

double calculateMSE ( const Pattern & pat )

virtual

Calculate the Mean Square Error respect to Pattern passed.

Implements LearningAlgorithm.

Definition at line 193 of file backpropagationalgo.cpp.

References NeuralNet::inputClusters(), Pattern::inputsOf(), LearningAlgorithm::neuralNet(), NeuralNet::outputClusters(), Pattern::outputsOf(), and NeuralNet::step().

void configure	(	ConfigurationParameters &	params,
		QString	prefix
	)

virtual

Configures the object using a ConfigurationParameters object.

From the file you can configure the parameters of the BackPropagation in this way:

[aBackPropagationGroup]
neuralnet = nameOfGroupOfTheNeuralNet
rate = learningRate      ;if it's not present, default is 0.0 !!
momentum = momentumRate  ;if it's not present, means momentum disabled
order = cluster2 linker1 cluster1 ; order of Cluster and Linker on which the error is backpropagated

As you can note, there is no configuration parameters for loading the learning set from here. This is intended. You need to load separately the learning set and call the method learn on the loaded learning set.

You can do that creating groups like the following (see class Pattern):

[learningSet:1]
cluster:1 = cluster1
inputs:1 = 1 2 3     ; input
cluster:2 = cluster2
outputs:2 = 2 4      ; desired output
[learningSet:2]
cluster:1 = cluster1
inputs:1 = 2 4 6     ; input
cluster:2 = cluster2
outputs:2 = 4 8      ; desired output
...
[learningSet:N]
cluster:1 = cluster1
inputs:1 = 10 20 30    ; input
cluster:2 = cluster2
outputs:2 = 20 40      ; desired output

And call the method LearningAlgorithm::loadPatternSet( params, "learningSet" )

Parameters

params	the configuration parameters object with parameters to use
prefix	the prefix to use to access the object configuration parameters. This is guaranteed to end with the separator character when called by the factory, so you don't need to add one

Implements ParameterSettableWithConfigureFunction.

Definition at line 247 of file backpropagationalgo.cpp.

References ConfigurationParameters::getObjectFromGroup(), ConfigurationParameters::getObjectFromParameter(), ConfigurationParameters::getValue(), LearningAlgorithm::setNeuralNet(), ConfigurationParameters::startRememberingGroupObjectAssociations(), and ConfigurationParameters::stopRememberingGroupObjectAssociations().

void describe ( QString type )

static

Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.

Definition at line 286 of file backpropagationalgo.cpp.

References ParameterSettable::addTypeDescription(), and ParameterSettable::IsMandatory.

void disableMomentum ( )

inline

Disable momentum.

Definition at line 97 of file backpropagationalgo.h.

void enableMomentum ( )

Enable the momentum.

Definition at line 95 of file backpropagationalgo.cpp.

DoubleVector getError ( Cluster * cl )

This method returns the deltas calculated by the Back-propagation Algorithm.

These deltas are set every time new targets are defined for the output layer(s), which are then used to update network weights when the method learn() is called.
They are also useful to calculate the network performance, but for that it must be used outside the learning cycle (a full learning iteration, that corresponds to present the network with all the patterns of the train data set). For that you must call getError( Cluster * anyOutputCluster ) for each line of your training set (you'll get a DoubleVector with the deltas for each unit of the cluster considered).
Then you can use those values to calculate your desired performance measure.
For instance: if you use it to calculate the Mean Square Error (MSE) of the network for your train data set you must accumulate the square of the the getError( anyOutputCluster ) output for each line of the set, and at the end divide it by the length of that same set (by definition the MSE is the sum of the squared differences between the target and actual output of a sequence of values). Getting the Root Mean Squared Error (RMSE) from this is trivial (you just need to calculate the square root of the MSE).

Warning: The data returned by getError( Cluster * ) is computed every time you set a new output target, which means every time you call the setTeachingInput( Cluster * anyOutputCluster, const DoubleVector & teaching_input ) method. If your network has more than one output layer you have to call setTeachingInput() for all the output clusters before calling getError() for any of the clusters.

Definition at line 86 of file backpropagationalgo.cpp.

void learn ( )

virtual

a single step of learning algorithm

Implements LearningAlgorithm.

Definition at line 132 of file backpropagationalgo.cpp.

Referenced by BackPropagationAlgo::learn().

void learn ( const Pattern & pat )

virtual

Starts a single training step.

Implements LearningAlgorithm.

Definition at line 177 of file backpropagationalgo.cpp.