DNF Class Reference

Main Deep Neuronal Network main class. More...

#include <dnf.h>

Public Member Functions
	DNF (const int NLAYERS, const int numTaps, double fs, Neuron::actMethod am=Neuron::Act_Tanh)
	Constructor which sets up the delay lines, network layers and also calculates the number of neurons per layer so that the final layer always just has one neuron. More...
double	filter (double signal, double noise)
	Realtime sample by sample filtering operation. More...
Net &	getNet () const
	Returns a reference to the whole neural network. More...
const int	getSignalDelaySteps () const
	Returns the length of the delay line which delays the signal polluted with noise. More...
const double	getDelayedSignal () const
	Returns the delayed with noise polluted signal by the delay indicated by getSignalDelaySteps(). More...
const double	getRemover () const
	Returns the remover signal. More...
const double	getOutput () const
	Returns the output of the DNF: the the noise free signal. More...
	~DNF ()
	Frees the memory used by the DNF.

Detailed Description

Main Deep Neuronal Network main class.

It's designed to be as simple as possible with only a few parameters as possible.

Constructor & Destructor Documentation

DNF()

DNF::DNF ( const int  NLAYERS, const int  numTaps, double  fs, Neuron::actMethod  am = Neuron::Act_Tanh  )

inline

Constructor which sets up the delay lines, network layers and also calculates the number of neurons per layer so that the final layer always just has one neuron.

Parameters

NLAYERS	Number of layers
numTaps	Number of taps for the delay line feeding into the 1st layer
fs	Sampling rate of the signals used in Hz.
am	The activation function for the neurons. Default is tanh.

Member Function Documentation

filter()

double DNF::filter ( double  signal, double  noise  )

inline

Realtime sample by sample filtering operation.

Parameters

signal	The signal contaminated with noise. Should be less than one.
noise	The reference noise. Should be less than one.

Returns

The filtered signal where the noise has been removed by the DNF.

getDelayedSignal()

const double DNF::getDelayedSignal ( ) const

inline

Returns the delayed with noise polluted signal by the delay indicated by getSignalDelaySteps().

Returns

The delayed noise polluted signal sample.

getNet()

Net& DNF::getNet ( ) const

inline

Returns a reference to the whole neural network.

Returns

A reference to Net.

getOutput()

const double DNF::getOutput ( ) const

inline

Returns the output of the DNF: the the noise free signal.

Returns

The current output of the DNF which is idential to filter().

getRemover()

const double DNF::getRemover ( ) const

inline

Returns the remover signal.

Returns

The current remover signal sample.

getSignalDelaySteps()

const int DNF::getSignalDelaySteps ( ) const

inline

Returns the length of the delay line which delays the signal polluted with noise.

Returns

Number of delay steps in samples.

---

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

• dnf.h