FeedForwardNN Class Reference

#include <feedforwardnn.h>

Inheritance diagram for FeedForwardNN:

[legend]Collaboration diagram for FeedForwardNN:

[legend]List of all members.

---

Detailed Description

abstract class (interface) for feed forward rate based neural networks

Definition at line 11 of file feedforwardnn.h.

Public Member Functions
	FeedForwardNN ()
virtual	~FeedForwardNN ()
virtual void	init (unsigned int inputDim, unsigned int outputDim)=0
	initialisation of the network with the given number of input and output units
virtual const matrix::Matrix	process (const matrix::Matrix &input) const =0
	passive processing of the input
virtual const matrix::Matrix	learn (const matrix::Matrix &input, const matrix::Matrix &nom_output, double learnRateFactor=1)=0
virtual void	damp (double damping)=0
	damps the weights and the biases by multiplying (1-damping)
virtual unsigned int	getInputDim () const =0
	returns the number of input neurons
virtual unsigned int	getOutputDim () const =0
	returns the number of output neurons
Static Public Member Functions
static double	linear (double x)
static double	dlinear (double)
static double	tanh (double x)
static double	dtanh (double x)
static double	sigmoid (double x)
static double	dsigmoid (double x)

---

Constructor & Destructor Documentation

FeedForwardNN (   )  [inline]

Definition at line 13 of file feedforwardnn.h.

virtual ~FeedForwardNN (   )  [inline, virtual]

Definition at line 14 of file feedforwardnn.h.

---

Member Function Documentation

virtual void damp (  double  damping  )  [pure virtual]

damps the weights and the biases by multiplying (1-damping) Implemented in MultiLayerFFNN, and OneLayerFFNN.

static double dlinear (  double   )  [inline, static]

Definition at line 36 of file feedforwardnn.h.

static double dsigmoid (  double  x  )  [inline, static]

Definition at line 40 of file feedforwardnn.h.

static double dtanh (  double  x  )  [inline, static]

Definition at line 38 of file feedforwardnn.h.

virtual unsigned int getInputDim (   )  const [pure virtual]

returns the number of input neurons Implemented in MultiLayerFFNN, and OneLayerFFNN.

virtual unsigned int getOutputDim (   )  const [pure virtual]

returns the number of output neurons Implemented in MultiLayerFFNN, and OneLayerFFNN.

virtual void init (  unsigned int  inputDim, unsigned int  outputDim )  [pure virtual]

initialisation of the network with the given number of input and output units Implemented in MultiLayerFFNN, and OneLayerFFNN.

virtual const matrix::Matrix learn (  const matrix::Matrix &  input, const matrix::Matrix &  nom_output, double  learnRateFactor = 1 )  [pure virtual]

Implemented in MultiLayerFFNN, and OneLayerFFNN.

static double linear (  double  x  )  [inline, static]

Definition at line 35 of file feedforwardnn.h.

virtual const matrix::Matrix process (  const matrix::Matrix &  input  )  const [pure virtual]

passive processing of the input Implemented in MultiLayerFFNN, and OneLayerFFNN.

static double sigmoid (  double  x  )  [inline, static]

Definition at line 39 of file feedforwardnn.h.

static double tanh (  double  x  )  [inline, static]

Definition at line 37 of file feedforwardnn.h.

---