Artificial Neural Networks - Multi-Layer Perceptrons. More...

#include <ml.hpp>

Public Types
enum	TrainingMethods { BACKPROP = 0, RPROP = 1 }
	Available training methods. More...
enum	ActivationFunctions { IDENTITY = 0, SIGMOID_SYM = 1, GAUSSIAN = 2 }
	possible activation functions More...
enum	TrainFlags { UPDATE_WEIGHTS = 1, NO_INPUT_SCALE = 2, NO_OUTPUT_SCALE = 4 }
	Train options. More...
enum	Flags { , RAW_OUTPUT = 1 }
	Predict options. More...
Public Member Functions
virtual CV_WRAP void	setTrainMethod (int method, double param1=0, double param2=0)=0
	Sets training method and common parameters.
virtual CV_WRAP int	getTrainMethod () const =0
	Returns current training method.
virtual CV_WRAP void	setActivationFunction (int type, double param1=0, double param2=0)=0
	Initialize the activation function for each neuron.
virtual CV_WRAP void	setLayerSizes (InputArray _layer_sizes)=0
	Integer vector specifying the number of neurons in each layer including the input and output layers.
virtual CV_WRAP cv::Mat	getLayerSizes () const =0
	Integer vector specifying the number of neurons in each layer including the input and output layers.
virtual CV_WRAP TermCriteria	getTermCriteria () const =0
	Termination criteria of the training algorithm.
virtual CV_WRAP void	setTermCriteria (TermCriteria val)=0
	Termination criteria of the training algorithm.
virtual CV_WRAP double	getBackpropWeightScale () const =0
	BPROP: Strength of the weight gradient term.
virtual CV_WRAP void	setBackpropWeightScale (double val)=0
	BPROP: Strength of the weight gradient term.
virtual CV_WRAP double	getBackpropMomentumScale () const =0
	BPROP: Strength of the momentum term (the difference between weights on the 2 previous iterations).
virtual CV_WRAP void	setBackpropMomentumScale (double val)=0
	BPROP: Strength of the momentum term (the difference between weights on the 2 previous iterations).
virtual CV_WRAP double	getRpropDW0 () const =0
	RPROP: Initial value $\Delta_0$ of update-values $\Delta_{ij}$ .
virtual CV_WRAP void	setRpropDW0 (double val)=0
	RPROP: Initial value $\Delta_0$ of update-values $\Delta_{ij}$ .
virtual CV_WRAP double	getRpropDWPlus () const =0
	RPROP: Increase factor $\eta^+$ .
virtual CV_WRAP void	setRpropDWPlus (double val)=0
	RPROP: Increase factor $\eta^+$ .
virtual CV_WRAP double	getRpropDWMinus () const =0
	RPROP: Decrease factor $\eta^-$ .
virtual CV_WRAP void	setRpropDWMinus (double val)=0
	RPROP: Decrease factor $\eta^-$ .
virtual CV_WRAP double	getRpropDWMin () const =0
	RPROP: Update-values lower limit $\Delta_{min}$ .
virtual CV_WRAP void	setRpropDWMin (double val)=0
	RPROP: Update-values lower limit $\Delta_{min}$ .
virtual CV_WRAP double	getRpropDWMax () const =0
	RPROP: Update-values upper limit $\Delta_{max}$ .
virtual CV_WRAP void	setRpropDWMax (double val)=0
	RPROP: Update-values upper limit $\Delta_{max}$ .
virtual CV_WRAP int	getVarCount () const =0
	Returns the number of variables in training samples.
virtual CV_WRAP bool	empty () const
	Returns true if the Algorithm is empty (e.g.
virtual CV_WRAP bool	isTrained () const =0
	Returns true if the model is trained.
virtual CV_WRAP bool	isClassifier () const =0
	Returns true if the model is classifier.
virtual CV_WRAP bool	train (const Ptr< TrainData > &trainData, int flags=0)
	Trains the statistical model.
virtual CV_WRAP bool	train (InputArray samples, int layout, InputArray responses)
	Trains the statistical model.
virtual CV_WRAP float	calcError (const Ptr< TrainData > &data, bool test, OutputArray resp) const
	Computes error on the training or test dataset.
virtual CV_WRAP float	predict (InputArray samples, OutputArray results=noArray(), int flags=0) const =0
	Predicts response(s) for the provided sample(s)
virtual CV_WRAP void	clear ()
	Clears the algorithm state.
virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage.
virtual void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage.
virtual CV_WRAP void	save (const String &filename) const
	Saves the algorithm to a file.
virtual CV_WRAP String	getDefaultName () const
	Returns the algorithm string identifier.
Static Public Member Functions
static CV_WRAP Ptr< ANN_MLP >	create ()
	Creates empty model.
template<typename _Tp >
static Ptr< _Tp >	train (const Ptr< TrainData > &data, int flags=0)
	Create and train model with default parameters.
template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node.
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file.
template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String.

Detailed Description

Artificial Neural Networks - Multi-Layer Perceptrons.

Unlike many other models in ML that are constructed and trained at once, in the MLP model these steps are separated. First, a network with the specified topology is created using the non-default constructor or the method ANN_MLP::create. All the weights are set to zeros. Then, the network is trained using a set of input and output vectors. The training procedure can be repeated more than once, that is, the weights can be adjusted based on the new training data.

Additional flags for StatModel::train are available: ANN_MLP::TrainFlags.

See also:: ml_intro_ann

Definition at line 1254 of file ml.hpp.

Member Enumeration Documentation

enum ActivationFunctions

possible activation functions

Enumerator:

IDENTITY

Identity function: $f(x)=x$ .

SIGMOID_SYM

Symmetrical sigmoid: $f(x)=\beta*(1-e^{-\alpha x})/(1+e^{-\alpha x}$ .

Note:: If you are using the default sigmoid activation function with the default parameter values fparam1=0 and fparam2=0 then the function used is y = 1.7159\*tanh(2/3 \* x), so the output will range from [-1.7159, 1.7159], instead of [0,1].

GAUSSIAN

Gaussian function: $f(x)=\beta e^{-\alpha x*x}$ .

Definition at line 1354 of file ml.hpp.

enum Flags [inherited]

Predict options.

Enumerator:

RAW_OUTPUT

makes the method return the raw results (the sum), not the class label

Reimplemented in DTrees.

Definition at line 296 of file ml.hpp.

enum TrainFlags

Train options.

Enumerator:

UPDATE_WEIGHTS

Update the network weights, rather than compute them from scratch.

In the latter case the weights are initialized using the Nguyen-Widrow algorithm.

NO_INPUT_SCALE

Do not normalize the input vectors.

If this flag is not set, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation equal to 1. If the network is assumed to be updated frequently, the new training data could be much different from original one. In this case, you should take care of proper normalization.

NO_OUTPUT_SCALE

Do not normalize the output vectors.

If the flag is not set, the training algorithm normalizes each output feature independently, by transforming it to the certain range depending on the used activation function.

Definition at line 1368 of file ml.hpp.

enum TrainingMethods

Available training methods.

Enumerator:

BACKPROP	The back-propagation algorithm.
RPROP	The RPROP algorithm. See RPROP93 for details.

Definition at line 1258 of file ml.hpp.

Member Function Documentation

virtual CV_WRAP float calcError	(	const Ptr< TrainData > &	data,
		bool	test,
		OutputArray	resp
	)		const `[virtual, inherited]`

Computes error on the training or test dataset.

Parameters:

data	the training data
test	if true, the error is computed over the test subset of the data, otherwise it's computed over the training subset of the data. Please note that if you loaded a completely different dataset to evaluate already trained classifier, you will probably want not to set the test subset at all with TrainData::setTrainTestSplitRatio and specify test=false, so that the error is computed for the whole new set. Yes, this sounds a bit confusing.
resp	the optional output responses.

The method uses StatModel::predict to compute the error. For regression models the error is computed as RMS, for classifiers - as a percent of missclassified samples (0-100%).

virtual CV_WRAP void clear ( ) [virtual, inherited]

Clears the algorithm state.

Reimplemented in DescriptorMatcher, and FlannBasedMatcher.

Definition at line 2984 of file core.hpp.

static CV_WRAP Ptr<ANN_MLP> create ( ) [static]

Creates empty model.

Use StatModel::train to train the model, Algorithm::load<ANN_MLP>(filename) to load the pre-trained model. Note that the train method has optional flags: ANN_MLP::TrainFlags.

virtual CV_WRAP bool empty ( ) const [virtual, inherited]

Returns true if the Algorithm is empty (e.g.

in the very beginning or after unsuccessful read

Reimplemented from Algorithm.

virtual CV_WRAP double getBackpropMomentumScale ( ) const [pure virtual]

BPROP: Strength of the momentum term (the difference between weights on the 2 previous iterations).

This parameter provides some inertia to smooth the random fluctuations of the weights. It can vary from 0 (the feature is disabled) to 1 and beyond. The value 0.1 or so is good enough. Default value is 0.1.

See also:: setBackpropMomentumScale

virtual CV_WRAP double getBackpropWeightScale ( ) const [pure virtual]

BPROP: Strength of the weight gradient term.

The recommended value is about 0.1. Default value is 0.1.

See also:: setBackpropWeightScale

virtual CV_WRAP String getDefaultName ( ) const [virtual, inherited]

Returns the algorithm string identifier.

This string is used as top level xml/yml node tag when the object is saved to a file or string.

virtual CV_WRAP cv::Mat getLayerSizes ( ) const [pure virtual]

Integer vector specifying the number of neurons in each layer including the input and output layers.

The very first element specifies the number of elements in the input layer. The last element - number of elements in the output layer.

See also:: setLayerSizes

virtual CV_WRAP double getRpropDW0 ( ) const [pure virtual]

RPROP: Initial value $\Delta_0$ of update-values $\Delta_{ij}$ .

Default value is 0.1.

See also:: setRpropDW0

virtual CV_WRAP double getRpropDWMax ( ) const [pure virtual]

RPROP: Update-values upper limit $\Delta_{max}$ .

It must be >1. Default value is 50.

See also:: setRpropDWMax

virtual CV_WRAP double getRpropDWMin ( ) const [pure virtual]

RPROP: Update-values lower limit $\Delta_{min}$ .

It must be positive. Default value is FLT_EPSILON.

See also:: setRpropDWMin

virtual CV_WRAP double getRpropDWMinus ( ) const [pure virtual]

RPROP: Decrease factor $\eta^-$ .

It must be <1. Default value is 0.5.

See also:: setRpropDWMinus

virtual CV_WRAP double getRpropDWPlus ( ) const [pure virtual]

RPROP: Increase factor $\eta^+$ .

It must be >1. Default value is 1.2.

See also:: setRpropDWPlus

virtual CV_WRAP TermCriteria getTermCriteria ( ) const [pure virtual]

Termination criteria of the training algorithm.

You can specify the maximum number of iterations (maxCount) and/or how much the error could change between the iterations to make the algorithm continue (epsilon). Default value is TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 1000, 0.01).

See also:: setTermCriteria

virtual CV_WRAP int getTrainMethod ( ) const [pure virtual]

Returns current training method.

virtual CV_WRAP int getVarCount ( ) const [pure virtual, inherited]

Returns the number of variables in training samples.

virtual CV_WRAP bool isClassifier ( ) const [pure virtual, inherited]

Returns true if the model is classifier.

virtual CV_WRAP bool isTrained ( ) const [pure virtual, inherited]

Returns true if the model is trained.

static Ptr<_Tp> load	(	const String &	filename,
		const String &	objname = `String()`
	)		`[static, inherited]`

Loads algorithm from the file.

Parameters:

filename	Name of the file to read.
objname	The optional name of the node to read (if empty, the first top-level node will be used)

This is static template method of Algorithm. It's usage is following (in the case of SVM):

     Ptr<SVM> svm = Algorithm::load<SVM>("my_svm_model.xml");

In order to make this method work, the derived class must overwrite Algorithm::read(const FileNode& fn).

Definition at line 3027 of file core.hpp.

static Ptr<_Tp> loadFromString	(	const String &	strModel,
		const String &	objname = `String()`
	)		`[static, inherited]`

Loads algorithm from a String.

Parameters:

strModel	The string variable containing the model you want to load.
objname	The optional name of the node to read (if empty, the first top-level node will be used)

This is static template method of Algorithm. It's usage is following (in the case of SVM):

     Ptr<SVM> svm = Algorithm::loadFromString<SVM>(myStringModel);

Definition at line 3046 of file core.hpp.

virtual CV_WRAP float predict	(	InputArray	samples,
		OutputArray	results = `noArray()`,
		int	flags = `0`
	)		const `[pure virtual, inherited]`

Predicts response(s) for the provided sample(s)

Parameters:

samples	The input samples, floating-point matrix
results	The optional output matrix of results.
flags	The optional flags, model-dependent. See cv::ml::StatModel::Flags.

Implemented in LogisticRegression.

virtual void read ( const FileNode & fn ) [virtual, inherited]

Reads algorithm parameters from a file storage.

Reimplemented in DescriptorMatcher, and FlannBasedMatcher.

Definition at line 2992 of file core.hpp.

static Ptr<_Tp> read ( const FileNode & fn ) [static, inherited]

Reads algorithm from the file node.

This is static template method of Algorithm. It's usage is following (in the case of SVM):

     Ptr<SVM> svm = Algorithm::read<SVM>(fn);

In order to make this method work, the derived class must overwrite Algorithm::read(const FileNode& fn) and also have static create() method without parameters (or with all the optional parameters)

Reimplemented in DescriptorMatcher, and FlannBasedMatcher.

Definition at line 3008 of file core.hpp.

virtual CV_WRAP void save ( const String & filename ) const [virtual, inherited]

Saves the algorithm to a file.

In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

virtual CV_WRAP void setActivationFunction	(	int	type,
		double	param1 = `0`,
		double	param2 = `0`
	)		`[pure virtual]`

Initialize the activation function for each neuron.

Currently the default and the only fully supported activation function is ANN_MLP::SIGMOID_SYM.

Parameters:

type	The type of activation function. See ANN_MLP::ActivationFunctions.
param1	The first parameter of the activation function, $\alpha$ . Default value is 0.
param2	The second parameter of the activation function, $\beta$ . Default value is 0.

virtual CV_WRAP void setBackpropMomentumScale ( double val ) [pure virtual]

BPROP: Strength of the momentum term (the difference between weights on the 2 previous iterations).

See also:: getBackpropMomentumScale

virtual CV_WRAP void setBackpropWeightScale ( double val ) [pure virtual]

BPROP: Strength of the weight gradient term.

See also:: getBackpropWeightScale

virtual CV_WRAP void setLayerSizes ( InputArray _layer_sizes ) [pure virtual]

Integer vector specifying the number of neurons in each layer including the input and output layers.

The very first element specifies the number of elements in the input layer. The last element - number of elements in the output layer. Default value is empty Mat.

See also:: getLayerSizes

virtual CV_WRAP void setRpropDW0 ( double val ) [pure virtual]

RPROP: Initial value $\Delta_0$ of update-values $\Delta_{ij}$ .

See also:: getRpropDW0

virtual CV_WRAP void setRpropDWMax ( double val ) [pure virtual]

RPROP: Update-values upper limit $\Delta_{max}$ .

See also:: getRpropDWMax

virtual CV_WRAP void setRpropDWMin ( double val ) [pure virtual]

RPROP: Update-values lower limit $\Delta_{min}$ .

See also:: getRpropDWMin

virtual CV_WRAP void setRpropDWMinus ( double val ) [pure virtual]

RPROP: Decrease factor $\eta^-$ .

See also:: getRpropDWMinus

virtual CV_WRAP void setRpropDWPlus ( double val ) [pure virtual]

RPROP: Increase factor $\eta^+$ .

See also:: getRpropDWPlus

virtual CV_WRAP void setTermCriteria ( TermCriteria val ) [pure virtual]

Termination criteria of the training algorithm.

See also:: getTermCriteria

virtual CV_WRAP void setTrainMethod	(	int	method,
		double	param1 = `0`,
		double	param2 = `0`
	)		`[pure virtual]`

Sets training method and common parameters.

Parameters:

method	Default value is ANN_MLP::RPROP. See ANN_MLP::TrainingMethods.
param1	passed to setRpropDW0 for ANN_MLP::RPROP and to setBackpropWeightScale for ANN_MLP::BACKPROP
param2	passed to setRpropDWMin for ANN_MLP::RPROP and to setBackpropMomentumScale for ANN_MLP::BACKPROP.

virtual CV_WRAP bool train	(	const Ptr< TrainData > &	trainData,
		int	flags = `0`
	)		`[virtual, inherited]`

Trains the statistical model.

Parameters:

trainData	training data that can be loaded from file using TrainData::loadFromCSV or created with TrainData::create.
flags	optional flags, depending on the model. Some of the models can be updated with the new training samples, not completely overwritten (such as NormalBayesClassifier or ANN_MLP).

static Ptr<_Tp> train	(	const Ptr< TrainData > &	data,
		int	flags = `0`
	)		`[static, inherited]`

Create and train model with default parameters.

The class must implement static `create()` method with no parameters or with all default parameter values

Definition at line 357 of file ml.hpp.

virtual CV_WRAP bool train	(	InputArray	samples,
		int	layout,
		InputArray	responses
	)		`[virtual, inherited]`

Trains the statistical model.

Parameters:

samples	training samples
layout	See ml::SampleTypes.
responses	vector of responses associated with the training samples.

virtual void write ( FileStorage & fs ) const [virtual, inherited]

Stores algorithm parameters in a file storage.

Reimplemented in DescriptorMatcher, and FlannBasedMatcher.

Definition at line 2988 of file core.hpp.

Type:	Program
Mbed OS support:	Mbed 2 deprecated
Created:	31 Mar 2016
Imports:	152
Forks:	0
Commits:	1
Dependents:	0
Dependencies:	1
Followers:	2

ANN_MLP Class Reference
[Machine Learning]

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Member Enumeration Documentation

Member Function Documentation

Repository toolbox

Repository details

Important Information for this Arm website

ANN_MLP Class Reference [Machine Learning]

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Member Enumeration Documentation

Member Function Documentation

Repository toolbox

Repository details

Important Information for this Arm website

Access Warning

ANN_MLP Class Reference
[Machine Learning]