Linear Prediction with optional activation function. More...

#include <shark/Models/LinearModel.h>

Inheritance diagram for shark::LinearModel< InputType, ActivationFunction >:

Public Types
typedef blas::vector< typename InputType::value_type, typename InputType::device_type >	VectorType

typedef blas::matrix< typename InputType::value_type, blas::row_major, typename InputType::device_type >	MatrixType

typedef base_type::BatchInputType	BatchInputType

typedef base_type::BatchOutputType	BatchOutputType

typedef base_type::ParameterVectorType	ParameterVectorType

Public Types inherited from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >
enum	Feature { HAS_FIRST_PARAMETER_DERIVATIVE = 1 , HAS_FIRST_INPUT_DERIVATIVE = 4 }

typedef InputTypeT	InputType
	Defines the input type of the model.

typedef OutputTypeT	OutputType
	Defines the output type of the model.

typedef AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >	ModelBaseType
	Defines the BaseType used by the model (this type). Useful for creating derived models.

typedef Batch< InputType >::type	BatchInputType
	defines the batch type of the input type.

typedef Batch< OutputType >::type	BatchOutputType
	defines the batch type of the output type

typedef TypedFlags< Feature >	Features

typedef TypedFeatureNotAvailableException< Feature >	FeatureNotAvailableException

Public Types inherited from shark::IParameterizable< VectorType >
typedef VectorType	ParameterVectorType

Public Member Functions
	LinearModel ()
	CDefault Constructor; use setStructure later.

	LinearModel (Shape const &inputs, Shape const &outputs=1, bool offset=false)
	Constructor creating a model with given dimensionalities and optional offset term.

std::string	name () const
	From INameable: return the class name.

	LinearModel (MatrixType const &matrix, VectorType const &offset=VectorType())
	Construction from matrix (and vector)

bool	hasOffset () const
	check for the presence of an offset term

Shape	inputShape () const
	Returns the expected shape of the input.

Shape	outputShape () const
	Returns the shape of the output.

ParameterVectorType	parameterVector () const
	obtain the parameter vector

void	setParameterVector (ParameterVectorType const &newParameters)
	overwrite the parameter vector

size_t	numberOfParameters () const
	return the number of parameter

void	setStructure (Shape const &inputs, Shape const &outputs=1, bool offset=false)
	overwrite structure and parameters

void	setStructure (MatrixType const &matrix, VectorType const &offset=VectorType())
	overwrite structure and parameters

MatrixType const &	matrix () const
	return a copy of the matrix in dense format

MatrixType &	matrix ()

VectorType const &	offset () const
	return the offset

VectorType &	offset ()

ActivationFunction const &	activationFunction () const
	Returns the activation function.

ActivationFunction &	activationFunction ()
	Returns the activation function.

boost::shared_ptr< State >	createState () const
	Creates an internal state of the model.

void	eval (BatchInputType const &inputs, BatchOutputType &outputs) const
	Evaluate the model: output = matrix * input + offset.

void	eval (InputType const &input, VectorType &output) const

void	eval (BatchInputType const &inputs, BatchOutputType &outputs, State &state) const
	Evaluate the model: output = matrix * input + offset.

void	weightedParameterDerivative (BatchInputType const &patterns, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, ParameterVectorType &gradient) const
	Calculates the first derivative w.r.t the parameters and summing them up over all patterns of the last computed batch.

void	weightedInputDerivative (BatchInputType const &patterns, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, MatrixType &derivative) const
	Calculates the first derivative w.r.t the inputs and summs them up over all patterns of the last computed batch.

void	weightedDerivatives (BatchInputType const &patterns, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, ParameterVectorType &parameterDerivative, MatrixType &inputDerivative) const

void	read (InArchive &archive)
	From ISerializable.

void	write (OutArchive &archive) const
	From ISerializable.

virtual void	eval (BatchInputType const &patterns, BatchOutputType &outputs) const
	Standard interface for evaluating the response of the model to a batch of patterns.

virtual void	eval (BatchInputType const &patterns, BatchOutputType &outputs, State &state) const=0
	Standard interface for evaluating the response of the model to a batch of patterns.

virtual void	eval (InputType const &pattern, OutputType &output) const
	Standard interface for evaluating the response of the model to a single pattern.

Public Member Functions inherited from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >
	AbstractModel ()

virtual	~AbstractModel ()

const Features &	features () const

virtual void	updateFeatures ()

bool	hasFirstParameterDerivative () const
	Returns true when the first parameter derivative is implemented.

bool	hasFirstInputDerivative () const
	Returns true when the first input derivative is implemented.

Data< OutputType >	operator() (Data< InputType > const &patterns) const
	Model evaluation as an operator for a whole dataset. This is a convenience function.

OutputType	operator() (InputType const &pattern) const
	Model evaluation as an operator for a single pattern. This is a convenience function.

BatchOutputType	operator() (BatchInputType const &patterns) const
	Model evaluation as an operator for a single pattern. This is a convenience function.

virtual void	weightedParameterDerivative (BatchInputType const &pattern, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, ParameterVectorType &derivative) const
	calculates the weighted sum of derivatives w.r.t the parameters.

virtual void	weightedInputDerivative (BatchInputType const &pattern, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, BatchInputType &derivative) const
	calculates the weighted sum of derivatives w.r.t the inputs

virtual void	weightedDerivatives (BatchInputType const &patterns, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, ParameterVectorType &parameterDerivative, BatchInputType &inputDerivative) const
	calculates weighted input and parameter derivative at the same time

Public Member Functions inherited from shark::IParameterizable< VectorType >
virtual	~IParameterizable ()

virtual void	setParameterVector (ParameterVectorType const &newParameters)
	Set the parameter vector.

Public Member Functions inherited from shark::INameable
virtual	~INameable ()

Public Member Functions inherited from shark::ISerializable
virtual	~ISerializable ()
	Virtual d'tor.

void	load (InArchive &archive, unsigned int version)
	Versioned loading of components, calls read(...).

void	save (OutArchive &archive, unsigned int version) const
	Versioned storing of components, calls write(...).

	BOOST_SERIALIZATION_SPLIT_MEMBER ()

Additional Inherited Members
Protected Attributes inherited from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >
Features	m_features

Detailed Description

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>
class shark::LinearModel< InputType, ActivationFunction >

Linear Prediction with optional activation function.

: This model computes the result of \( y = f(x) = g(A x + b) \), where g is an arbitrary activation function, see Neuron activation functions.. By default g is the identity and the model is a simple linear model. Otherwise, this is known as a generalized linear model. There are two important special cases: The output may be a single number, and the offset term b may be dropped.

The class allows for dense and sparse input vector types. However it assumes that the weight matrix and the ouputs are dense. There are some cases where this is not good behavior. Check for example Normalizer for a class which is designed for sparse inputs and outputs.

Definition at line 59 of file LinearModel.h.

Member Typedef Documentation

◆ BatchInputType

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

typedef base_type::BatchInputType shark::LinearModel< InputType, ActivationFunction >::BatchInputType

Definition at line 76 of file LinearModel.h.

◆ BatchOutputType

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

typedef base_type::BatchOutputType shark::LinearModel< InputType, ActivationFunction >::BatchOutputType

Definition at line 77 of file LinearModel.h.

◆ MatrixType

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

typedef blas::matrix<typename InputType::value_type, blas::row_major, typename InputType::device_type> shark::LinearModel< InputType, ActivationFunction >::MatrixType

Definition at line 66 of file LinearModel.h.

◆ ParameterVectorType

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

typedef base_type::ParameterVectorType shark::LinearModel< InputType, ActivationFunction >::ParameterVectorType

Definition at line 78 of file LinearModel.h.

◆ VectorType

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

typedef blas::vector<typename InputType::value_type, typename InputType::device_type> shark::LinearModel< InputType, ActivationFunction >::VectorType

Definition at line 65 of file LinearModel.h.

Constructor & Destructor Documentation

◆ LinearModel() [1/3]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

shark::LinearModel< InputType, ActivationFunction >::LinearModel ( )

inline

CDefault Constructor; use setStructure later.

Definition at line 81 of file LinearModel.h.

References shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_INPUT_DERIVATIVE, shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_PARAMETER_DERIVATIVE, and shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::m_features.

◆ LinearModel() [2/3]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

shark::LinearModel< InputType, ActivationFunction >::LinearModel	(	Shape const &	inputs,
		Shape const &	outputs = `1`,
		bool	offset = `false`
	)

inline

Constructor creating a model with given dimensionalities and optional offset term.

Definition at line 88 of file LinearModel.h.

References shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_INPUT_DERIVATIVE, shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_PARAMETER_DERIVATIVE, and shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::m_features.

◆ LinearModel() [3/3]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

shark::LinearModel< InputType, ActivationFunction >::LinearModel	(	MatrixType const &	matrix,
		VectorType const &	offset = `VectorType()`
	)

inline

Construction from matrix (and vector)

Definition at line 104 of file LinearModel.h.

References shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_INPUT_DERIVATIVE, shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::HAS_FIRST_PARAMETER_DERIVATIVE, and shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::m_features.

Member Function Documentation

◆ activationFunction() [1/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

ActivationFunction & shark::LinearModel< InputType, ActivationFunction >::activationFunction ( )

inline

Returns the activation function.

Definition at line 182 of file LinearModel.h.

◆ activationFunction() [2/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

ActivationFunction const & shark::LinearModel< InputType, ActivationFunction >::activationFunction ( ) const

inline

Returns the activation function.

Definition at line 177 of file LinearModel.h.

◆ createState()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

boost::shared_ptr< State > shark::LinearModel< InputType, ActivationFunction >::createState ( ) const

inlinevirtual

Creates an internal state of the model.

The state is needed when the derivatives are to be calculated. Eval can store a state which is then reused to speed up the calculations of the derivatives. This also allows eval to be evaluated in parallel!

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 186 of file LinearModel.h.

◆ eval() [1/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::eval	(	BatchInputType const &	inputs,
		BatchOutputType &	outputs
	)		const

inlinevirtual

Evaluate the model: output = matrix * input + offset.

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 193 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::hasOffset().

◆ eval() [2/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::eval	(	BatchInputType const &	inputs,
		BatchOutputType &	outputs,
		State &	state
	)		const

inlinevirtual

Evaluate the model: output = matrix * input + offset.

Implements shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 213 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::hasOffset(), and shark::State::toState().

◆ eval() [3/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

virtual void shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::eval	(	BatchInputType const &	patterns,
		BatchOutputType &	outputs
	)		const

inlinevirtual

Standard interface for evaluating the response of the model to a batch of patterns.

Parameters

patterns	the inputs of the model
outputs	the predictions or response of the model to every pattern

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 163 of file AbstractModel.h.

◆ eval() [4/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

virtual void shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::eval	(	BatchInputType const &	patterns,
		BatchOutputType &	outputs,
		State &	state
	)		const

virtual

Standard interface for evaluating the response of the model to a batch of patterns.

Parameters

patterns	the inputs of the model
outputs	the predictions or response of the model to every pattern
state	intermediate results stored by eval which can be reused for derivative computation.

Implements shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

◆ eval() [5/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::eval	(	InputType const &	input,
		VectorType &	output
	)		const

inline

Definition at line 203 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::hasOffset().

◆ eval() [6/6]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

virtual void shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >::eval	(	InputType const &	pattern,
		OutputType &	output
	)		const

inlinevirtual

Standard interface for evaluating the response of the model to a single pattern.

Parameters

pattern	the input of the model
output	the prediction or response of the model to the pattern

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 179 of file AbstractModel.h.

◆ hasOffset()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

bool shark::LinearModel< InputType, ActivationFunction >::hasOffset ( ) const

inline

check for the presence of an offset term

Definition at line 116 of file LinearModel.h.

Referenced by shark::LinearModel< InputType, ActivationFunction >::eval(), shark::LinearModel< InputType, ActivationFunction >::eval(), shark::LinearModel< InputType, ActivationFunction >::eval(), shark::LinearModel< InputType, ActivationFunction >::weightedDerivatives(), and shark::LinearModel< InputType, ActivationFunction >::weightedParameterDerivative().

◆ inputShape()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

Shape shark::LinearModel< InputType, ActivationFunction >::inputShape ( ) const

inlinevirtual

Returns the expected shape of the input.

Implements shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 121 of file LinearModel.h.

Referenced by shark::LinearModel< InputType, ActivationFunction >::setParameterVector(), shark::LinearModel< InputType, ActivationFunction >::weightedDerivatives(), and shark::LinearModel< InputType, ActivationFunction >::weightedParameterDerivative().

◆ matrix() [1/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

MatrixType & shark::LinearModel< InputType, ActivationFunction >::matrix ( )

inline

Definition at line 164 of file LinearModel.h.

◆ matrix() [2/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

MatrixType const & shark::LinearModel< InputType, ActivationFunction >::matrix ( ) const

inline

return a copy of the matrix in dense format

Definition at line 160 of file LinearModel.h.

Referenced by main(), main(), and shark::LinearModel< InputType, ActivationFunction >::setStructure().

◆ name()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

std::string shark::LinearModel< InputType, ActivationFunction >::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 100 of file LinearModel.h.

◆ numberOfParameters()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

size_t shark::LinearModel< InputType, ActivationFunction >::numberOfParameters ( ) const

inlinevirtual

return the number of parameter

Reimplemented from shark::IParameterizable< VectorType >.

Definition at line 143 of file LinearModel.h.

Referenced by shark::LinearModel< InputType, ActivationFunction >::weightedDerivatives(), and shark::LinearModel< InputType, ActivationFunction >::weightedParameterDerivative().

◆ offset() [1/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

VectorType & shark::LinearModel< InputType, ActivationFunction >::offset ( )

inline

Definition at line 172 of file LinearModel.h.

◆ offset() [2/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

VectorType const & shark::LinearModel< InputType, ActivationFunction >::offset ( ) const

inline

return the offset

Definition at line 169 of file LinearModel.h.

Referenced by main(), shark::LinearModel< InputType, ActivationFunction >::setStructure(), and shark::LinearModel< InputType, ActivationFunction >::setStructure().

◆ outputShape()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

Shape shark::LinearModel< InputType, ActivationFunction >::outputShape ( ) const

inlinevirtual

Returns the shape of the output.

Implements shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 125 of file LinearModel.h.

Referenced by main(), main(), shark::LinearModel< InputType, ActivationFunction >::setParameterVector(), shark::PCA::train(), shark::LinearModel< InputType, ActivationFunction >::weightedDerivatives(), and shark::LinearModel< InputType, ActivationFunction >::weightedParameterDerivative().

◆ parameterVector()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

ParameterVectorType shark::LinearModel< InputType, ActivationFunction >::parameterVector ( ) const

inlinevirtual

obtain the parameter vector

Reimplemented from shark::IParameterizable< VectorType >.

Definition at line 130 of file LinearModel.h.

Referenced by shark::SvmLogisticInterpretation< InputType >::evalDerivative().

◆ read()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::read ( InArchive & archive )

inlinevirtual

From ISerializable.

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 307 of file LinearModel.h.

◆ setParameterVector()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::setParameterVector ( ParameterVectorType const & newParameters )

inline

overwrite the parameter vector

Definition at line 135 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::inputShape(), shark::Shape::numElements(), and shark::LinearModel< InputType, ActivationFunction >::outputShape().

Referenced by main().

◆ setStructure() [1/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::setStructure	(	MatrixType const &	matrix,
		VectorType const &	offset = `VectorType()`
	)

inline

overwrite structure and parameters

Definition at line 154 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::matrix(), and shark::LinearModel< InputType, ActivationFunction >::offset().

◆ setStructure() [2/2]

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::setStructure	(	Shape const &	inputs,
		Shape const &	outputs = `1`,
		bool	offset = `false`
	)

inline

overwrite structure and parameters

Definition at line 148 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::offset().

Referenced by shark::LassoRegression< InputVectorType >::train(), and shark::NormalizeComponentsZCA::train().

◆ weightedDerivatives()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::weightedDerivatives	(	BatchInputType const &	patterns,
		BatchOutputType const &	outputs,
		BatchOutputType const &	coefficients,
		State const &	state,
		ParameterVectorType &	parameterDerivative,
		MatrixType &	inputDerivative
	)		const

inline

Definition at line 270 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::hasOffset(), shark::LinearModel< InputType, ActivationFunction >::inputShape(), shark::LinearModel< InputType, ActivationFunction >::numberOfParameters(), shark::Shape::numElements(), shark::LinearModel< InputType, ActivationFunction >::outputShape(), SIZE_CHECK, and shark::State::toState().

◆ weightedInputDerivative()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::weightedInputDerivative	(	BatchInputType const &	patterns,
		BatchOutputType const &	outputs,
		BatchOutputType const &	coefficients,
		State const &	state,
		MatrixType &	derivative
	)		const

inline

Calculates the first derivative w.r.t the inputs and summs them up over all patterns of the last computed batch.

Definition at line 252 of file LinearModel.h.

References SIZE_CHECK, and shark::State::toState().

◆ weightedParameterDerivative()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::weightedParameterDerivative	(	BatchInputType const &	patterns,
		BatchOutputType const &	outputs,
		BatchOutputType const &	coefficients,
		State const &	state,
		ParameterVectorType &	gradient
	)		const

inline

Calculates the first derivative w.r.t the parameters and summing them up over all patterns of the last computed batch.

Definition at line 224 of file LinearModel.h.

References shark::LinearModel< InputType, ActivationFunction >::hasOffset(), shark::LinearModel< InputType, ActivationFunction >::inputShape(), shark::LinearModel< InputType, ActivationFunction >::numberOfParameters(), shark::Shape::numElements(), shark::LinearModel< InputType, ActivationFunction >::outputShape(), SIZE_CHECK, and shark::State::toState().

◆ write()

template<class InputType = RealVector, class ActivationFunction = LinearNeuron>

void shark::LinearModel< InputType, ActivationFunction >::write ( OutArchive & archive ) const

inlinevirtual

From ISerializable.

Reimplemented from shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >.

Definition at line 314 of file LinearModel.h.

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

include/shark/Models/LinearModel.h

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ BatchInputType

◆ BatchOutputType

◆ MatrixType

◆ ParameterVectorType

◆ VectorType

Constructor & Destructor Documentation

◆ LinearModel() [1/3]

◆ LinearModel() [2/3]

◆ LinearModel() [3/3]

Member Function Documentation

◆ activationFunction() [1/2]

◆ activationFunction() [2/2]

◆ createState()

◆ eval() [1/6]

◆ eval() [2/6]

◆ eval() [3/6]

◆ eval() [4/6]

◆ eval() [5/6]

◆ eval() [6/6]

◆ hasOffset()

◆ inputShape()

◆ matrix() [1/2]

◆ matrix() [2/2]

◆ name()

◆ numberOfParameters()

◆ offset() [1/2]

◆ offset() [2/2]

◆ outputShape()

◆ parameterVector()

◆ read()

◆ setParameterVector()

◆ setStructure() [1/2]

◆ setStructure() [2/2]

◆ weightedDerivatives()

◆ weightedInputDerivative()

◆ weightedParameterDerivative()

◆ write()