OpenANN: OpenANN::Layer Class Reference

OpenANN 1.1.0

An open source library for artificial neural networks.

All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages

Interface that has to be implemented by all layers of a neural network that can be trained with backpropagation. More...

#include <Layer.h>

Inheritance diagram for OpenANN::Layer:

Public Member Functions
virtual	~Layer ()

virtual OutputInfo	initialize (std::vector< double * > &parameterPointers, std::vector< double * > &parameterDerivativePointers)=0
	Fill in the parameter pointers and parameter derivative pointers. More...

virtual void	initializeParameters ()=0
	Initialize the parameters. More...

virtual void	updatedParameters ()=0
	Generate internal parameters from externally visible parameters. More...

virtual void	forwardPropagate (Eigen::MatrixXd x, Eigen::MatrixXd &y, bool dropout, double *error=0)=0
	Forward propagation in this layer. More...

virtual void	backpropagate (Eigen::MatrixXd ein, Eigen::MatrixXd &eout, bool backpropToPrevious)=0
	Backpropagation in this layer. More...

virtual Eigen::MatrixXd &	getOutput ()=0
	Output after last forward propagation. More...

virtual Eigen::VectorXd	getParameters ()=0
	Get the current values of parameters (weights, biases, ...). More...

Detailed Description

Interface that has to be implemented by all layers of a neural network that can be trained with backpropagation.

Constructor & Destructor Documentation

virtual OpenANN::Layer::~Layer ( )

inlinevirtual

Member Function Documentation

virtual void OpenANN::Layer::backpropagate	(	Eigen::MatrixXd *	ein,
		Eigen::MatrixXd *&	eout,
		bool	backpropToPrevious
	)

pure virtual

Backpropagation in this layer.

Parameters

ein	pointer to error signal of the higher layer
eout	returns a pointer to error signal of the layer (derivative of the error with respect to the input)
backpropToPrevious	backpropagate errors to previous layers

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::SparseAutoEncoder, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual void OpenANN::Layer::forwardPropagate	(	Eigen::MatrixXd *	x,
		Eigen::MatrixXd *&	y,
		bool	dropout,
		double *	error = `0`
	)

pure virtual

Forward propagation in this layer.

Parameters

x	pointer to input of the layer (with bias)
y	returns a pointer to output of the layer
dropout	enable dropout for regularization
error	error value, will be updated with regularization terms

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::SparseAutoEncoder, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual Eigen::MatrixXd& OpenANN::Layer::getOutput ( )

pure virtual

Output after last forward propagation.

Returns: output

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::SparseAutoEncoder, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual Eigen::VectorXd OpenANN::Layer::getParameters ( )

pure virtual

Get the current values of parameters (weights, biases, ...).

Returns: parameters

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::SparseAutoEncoder, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual OutputInfo OpenANN::Layer::initialize	(	std::vector< double * > &	parameterPointers,
		std::vector< double * > &	parameterDerivativePointers
	)

pure virtual

Fill in the parameter pointers and parameter derivative pointers.

Parameters

parameterPointers	pointers to parameters
parameterDerivativePointers	pointers to derivatives of parameters

Returns: information about the output of the layer

Implemented in OpenANN::RBM, OpenANN::FullyConnected, OpenANN::SigmaPi, OpenANN::SparseAutoEncoder, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual void OpenANN::Layer::initializeParameters ( )

pure virtual

Initialize the parameters.

This is usually called before each optimization.

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::SparseAutoEncoder, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

virtual void OpenANN::Layer::updatedParameters ( )

pure virtual

Generate internal parameters from externally visible parameters.

This is usually called after each parameter update.

Implemented in OpenANN::SigmaPi, OpenANN::RBM, OpenANN::FullyConnected, OpenANN::SparseAutoEncoder, OpenANN::IntrinsicPlasticity, OpenANN::Convolutional, OpenANN::Subsampling, OpenANN::LocalResponseNormalization, OpenANN::Compressed, OpenANN::Extreme, OpenANN::AlphaBetaFilter, OpenANN::MaxPooling, OpenANN::Dropout, and OpenANN::Input.

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

OpenANN/layers/Layer.h