MultiLayerFFNN Class Reference

multi layer neural network with configurable activation functions More...

#include <multilayerffnn.h>

Inherits FeedForwardNN, and InvertableModel.

Inherited by Elman.

Inheritance diagram for MultiLayerFFNN:

[legend]Collaboration diagram for MultiLayerFFNN:

[legend]List of all members.

Public Member Functions
	MultiLayerFFNN (double eps, const std::vector< Layer > &layers)
virtual	~MultiLayerFFNN ()
virtual void	init (unsigned int inputDim, unsigned int outputDim, double unit_map=0.0)
	initialisation of the network with the given number of input and output units
virtual const matrix::Matrix	process (const matrix::Matrix &input)
	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 (process should be called before)
virtual const matrix::Matrix	response (const matrix::Matrix &input) const
virtual unsigned int	getInputDim () const
	returns the number of input neurons
virtual unsigned int	getOutputDim () const
	returns the number of output neurons
virtual void	damp (double damping)
	damps the weights and the biases by multiplying (1-damping)
bool	store (FILE *f) const
	stores the layer binary into file stream
bool	restore (FILE *f)
	restores the layer binary from file stream
virtual paramkey	getName () const
	return the name of the object
virtual paramval	getParam (const paramkey &key) const
	returns the value of the requested parameter or 0 (+ error message to stderr) if unknown.
virtual bool	setParam (const paramkey &key, paramval val)
	sets the value of the given parameter or does nothing if unknown.
virtual paramlist	getParamList () const
	The list of all parameters with there value as allocated lists.
virtual const Layer &	getLayer (unsigned int layer) const
virtual const matrix::Matrix &	getWeights (unsigned int to_layer) const
virtual const matrix::Matrix &	getBias (unsigned int of_layer) const
Protected Attributes
double	eps
std::vector< Layer >	layers
std::vector< matrix::Matrix >	weights
std::vector< matrix::Matrix >	bias
std::vector< matrix::Matrix >	ys
std::vector< matrix::Matrix >	zs
bool	initialised

---

Detailed Description

multi layer neural network with configurable activation functions

---

Constructor & Destructor Documentation

MultiLayerFFNN (  double  eps, const std::vector< Layer > &  layers )  [inline]

Parameters: eps  learning rate layers  Layer description (the input layer is not specified (always linear))

virtual ~MultiLayerFFNN (   )  [inline, virtual]

---

Member Function Documentation

void damp (  double  damping  )  [virtual]

damps the weights and the biases by multiplying (1-damping) Implements FeedForwardNN.

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

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

returns the number of input neurons Implements AbstractModel.

virtual const Layer& getLayer (  unsigned int  layer  )  const [inline, virtual]

virtual paramkey getName (   )  const [inline, virtual]

return the name of the object Reimplemented from Configurable. Reimplemented in Elman.

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

returns the number of output neurons Implements AbstractModel.

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

returns the value of the requested parameter or 0 (+ error message to stderr) if unknown. Reimplemented from Configurable.

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.

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

void init (  unsigned int  inputDim, unsigned int  outputDim, double  unit_map = 0.0 )  [virtual]

initialisation of the network with the given number of input and output units Implements AbstractModel. Reimplemented in Elman.

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 (process should be called before) Implements AbstractModel. Reimplemented in Elman.

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

passive processing of the input Implements AbstractModel. Reimplemented in Elman.

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

See also: InvertableModel::response (process should be called before) Implements InvertableModel.

bool restore (  FILE *  f  )  [virtual]

restores the layer binary from file stream Implements Storeable. Reimplemented in Elman.

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

sets the value of the given parameter or does nothing if unknown. Reimplemented from Configurable.

bool store (  FILE *  f  )  const [virtual]

stores the layer binary into file stream Implements Storeable. Reimplemented in Elman.

---

Member Data Documentation

std::vector<matrix::Matrix> bias [protected]

double eps [protected]

bool initialised [protected]

std::vector<Layer> layers [protected]

std::vector<matrix::Matrix> weights [protected]

std::vector<matrix::Matrix> ys [protected]

std::vector<matrix::Matrix> zs [protected]

---

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

• multilayerffnn.h
• multilayerffnn.cpp

---