AbstractModel Class Reference

abstract class (interface) for a model that can be used by a controller More...

#include <abstractmodel.h>

Inherits Configurable, Storeable, and Inspectable.

Inherited by InvertableModel, and SOM.

Inheritance diagram for AbstractModel:

[legend]Collaboration diagram for AbstractModel:

[legend]List of all members.

Public Member Functions
	AbstractModel ()
	AbstractModel (const std::string &name, const std::string &revision)
virtual	~AbstractModel ()
virtual void	init (unsigned int inputDim, unsigned int outputDim, double unit_map=0.0, RandGen *randGen=0)=0
	initialisation of the network with the given number of input and output units
virtual const matrix::Matrix	process (const matrix::Matrix &input)=0
	passive processing of the input (this function is not constant since a recurrent network for example might change internal states
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

---

Detailed Description

abstract class (interface) for a model that can be used by a controller

---

Constructor & Destructor Documentation

AbstractModel

(

)

[inline]

AbstractModel	(	const std::string &	name,
		const std::string &	revision
	)			[inline]

virtual ~AbstractModel

(

)

[inline, virtual]

---

Member Function Documentation

virtual void damp

(

double

damping

)

[pure virtual]

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

Implemented in Elman, FeedForwardNN, MultiLayerFFNN, OneLayerFFNN, and SOM.

virtual unsigned int getInputDim

(

)

const [pure virtual]

returns the number of input neurons

Implemented in MultiLayerFFNN, OneLayerFFNN, and SOM.

virtual unsigned int getOutputDim

(

)

const [pure virtual]

returns the number of output neurons

Implemented in MultiLayerFFNN, OneLayerFFNN, and SOM.

virtual void init	(	unsigned int	inputDim,
		unsigned int	outputDim,
		double	unit_map = 0.0,
		RandGen *	randGen = 0
	)			[pure virtual]

initialisation of the network with the given number of input and output units

Parameters:

	inputDim	length of input vector
	outputDim	length of output vector
	unit_map	if 0 the parametes are choosen randomly. Otherwise the model is initialised to represent a unit_map with the given response strength.
	randGen	pointer to random generator, if 0 an new one is used

Implemented in Elman, MultiLayerFFNN, OneLayerFFNN, and SOM.

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

Implemented in Elman, MultiLayerFFNN, OneLayerFFNN, and SOM.

virtual const matrix::Matrix process

(

const matrix::Matrix &

input

)

[pure virtual]

passive processing of the input (this function is not constant since a recurrent network for example might change internal states

Implemented in Elman, MultiLayerFFNN, OneLayerFFNN, and SOM.

---

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

• abstractmodel.h

---