OneLayerFFNN Class Reference

#include <onelayerffnn.h>

Inheritance diagram for OneLayerFFNN:

[legend]Collaboration diagram for OneLayerFFNN:

[legend]List of all members.

---

Detailed Description

simple one layer neural network with configurable activation function

Definition at line 7 of file onelayerffnn.h.

Public Member Functions
	OneLayerFFNN (double eps, double factor_bias=0.1)
	Uses linear activation function.
	OneLayerFFNN (double eps, double factor_bias, ActivationFunction actfun, ActivationFunction dactfun)
virtual	~OneLayerFFNN ()
virtual void	init (unsigned int inputDim, unsigned int outputDim)
	initialisation of the network with the given number of input and output units
virtual const matrix::Matrix	process (const matrix::Matrix &input) const
	passive processing of the input
virtual const matrix::Matrix	learn (const matrix::Matrix &input, const matrix::Matrix &nom_output, double learnRateFactor=1)
	performs learning and returns the network output before learning
virtual unsigned int	getInputDim () const
	returns the number of input neurons
virtual unsigned int	getOutputDim () const
	returns the number of output neurons
virtual const matrix::Matrix &	getWeights () const
virtual const matrix::Matrix &	getBias () const
virtual void	damp (double damping)
	damps the weights and the biases by multiplying (1-damping)
virtual paramkey	getName () const
	return the name of the object (with version number) Hint: { return "$ID$"; }
virtual paramval	getParam (const paramkey key) const
virtual bool	setParam (const paramkey key, paramval val)
virtual paramlist	getParamList () const
	The list of all parameters with there value as allocated lists.

---

Constructor & Destructor Documentation

OneLayerFFNN (  double  eps, double  factor_bias = 0.1 )  [inline]

Uses linear activation function. Parameters: eps  learning rate factor_bias  learning rate factor for bias learning Definition at line 14 of file onelayerffnn.h.

OneLayerFFNN (  double  eps, double  factor_bias, ActivationFunction  actfun, ActivationFunction  dactfun )  [inline]

Parameters: eps  learning rate factor_bias  learning rate factor for bias learning actfun  callback activation function (see FeedForwardNN) dactfun  callback for first derivative of the activation function Definition at line 28 of file onelayerffnn.h.

virtual ~OneLayerFFNN (   )  [inline, virtual]

Definition at line 35 of file onelayerffnn.h.

---

Member Function Documentation

virtual void damp (  double  damping  )  [inline, virtual]

damps the weights and the biases by multiplying (1-damping) Implements FeedForwardNN. Definition at line 61 of file onelayerffnn.h.

virtual const matrix::Matrix& getBias (   )  const [inline, virtual]

Definition at line 58 of file onelayerffnn.h.

virtual unsigned int getInputDim (   )  const [inline, virtual]

returns the number of input neurons Implements FeedForwardNN. Definition at line 49 of file onelayerffnn.h.

virtual paramkey getName (   )  const [inline, virtual]

return the name of the object (with version number) Hint: { return "$ID$"; } Reimplemented from Configurable. Definition at line 67 of file onelayerffnn.h.

virtual unsigned int getOutputDim (   )  const [inline, virtual]

returns the number of output neurons Implements FeedForwardNN. Definition at line 53 of file onelayerffnn.h.

virtual paramval getParam (  const paramkey  key  )  const [inline, virtual]

Definition at line 71 of file onelayerffnn.h.

virtual paramlist getParamList (   )  const [inline, virtual]

The list of all parameters with there value as allocated lists. Returns: list of key-value pairs Reimplemented from Configurable. Definition at line 83 of file onelayerffnn.h.

virtual const matrix::Matrix& getWeights (   )  const [inline, virtual]

Definition at line 57 of file onelayerffnn.h.

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

initialisation of the network with the given number of input and output units Implements FeedForwardNN. Definition at line 7 of file onelayerffnn.cpp.

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

performs learning and returns the network output before learning Implements FeedForwardNN. Definition at line 19 of file onelayerffnn.cpp.

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

passive processing of the input Implements FeedForwardNN. Definition at line 14 of file onelayerffnn.cpp.

virtual bool setParam (  const paramkey  key, paramval  val )  [inline, virtual]

Definition at line 76 of file onelayerffnn.h.

---