Applies a learnable filter on a 2D or 3D input. More...

#include <Convolutional.h>

Inheritance diagram for OpenANN::Convolutional:

Public Member Functions
	Convolutional (OutputInfo info, int featureMaps, int kernelRows, int kernelCols, bool bias, ActivationFunction act, double stdDev, Regularization regularization)

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

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

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

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

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

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

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

Public Member Functions inherited from OpenANN::Layer
virtual	~Layer ()

Detailed Description

Applies a learnable filter on a 2D or 3D input.

Hence, convolutional layers can be regarded as biologically inspired trainable feature extractors. Another perspective is that they combine weight sharing and sparse connections to reduce the number of weights drastically in contrast to fully connected layers.

Each feature map in this layer is connected to each feature map in the previous layer such that we use one convolution kernel for each of these connections. After convolving the input feature maps, an activation function will be applied on the activations.

Supports the following regularization types:

L1 penalty
L2 penalty

[1] Yann LeCun, Léon Bottou, Yoshua Bengio and Patrick Haffner: Gradient-Based Learning Applied to Document Recognition, Intelligent Signal Processing, IEEE Press, S. Haykin and B. Kosko (Eds.), pp. 306-351, 2001.

Constructor & Destructor Documentation

OpenANN::Convolutional::Convolutional	(	OutputInfo	info,
		int	featureMaps,
		int	kernelRows,
		int	kernelCols,
		bool	bias,
		ActivationFunction	act,
		double	stdDev,
		Regularization	regularization
	)

Member Function Documentation

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

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

Implements OpenANN::Layer.

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

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

Implements OpenANN::Layer.

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

virtual

Output after last forward propagation.

Returns: output

Implements OpenANN::Layer.

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

virtual

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

Returns: parameters

Implements OpenANN::Layer.

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