Fully connected layer with fixed random weights. More...

#include <Extreme.h>

Inheritance diagram for OpenANN::Extreme:

Public Member Functions
	Extreme (OutputInfo info, int J, bool bias, ActivationFunction act, double stdDev)

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

Fully connected layer with fixed random weights.

This kind of layer is used in Extreme Learning Machines (ELMs). It projects low dimensional data onto a higher dimensional space such that a linear classifier or regression algorithm in the next layer could approximate arbitrary functions. The advantage of this concept is that a closed form solution is available. The disadvantage is that the number of required nodes is usually much larger than in conventional multilayer neural networks.

[1] Guang-Bin Huang, Qin-Yu Zhu and Chee-Kheong Siew: Extreme learning machine: Theory and applications, Neurocomputing 70 (1–3), pp. 489-501, 2006.

Constructor & Destructor Documentation

OpenANN::Extreme::Extreme	(	OutputInfo	info,
		int	J,
		bool	bias,
		ActivationFunction	act,
		double	stdDev
	)

Member Function Documentation

virtual void OpenANN::Extreme::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::Extreme::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::Extreme::getOutput ( )

virtual

Output after last forward propagation.