Main Page   Namespace List   Class Hierarchy   Compound List   File List   Namespace Members   Compound Members   File Members   Related Pages  

annie::CenterNeuron Class Reference

#include <CenterNeuron.h>

Inheritance diagram for annie::CenterNeuron:

annie::Neuron List of all members.

Public Methods

 CenterNeuron (int label, int dimension)
 CenterNeuron (int label, VECTOR center)
 CenterNeuron (int label, int dimension, real center[])
virtual ~CenterNeuron ()
VECTOR getCenter ()
 Returns the center point. More...

virtual void setCenter (VECTOR center)
 Sets the center point. More...

virtual void setCenter (real center[])
 Sets the center point. More...

virtual void connect (Neuron *from)
 Sets the center-neuron to receive as input the output of the given neuron. More...

virtual std::string toString ()
 
See also:
Neuron::toString.
More...


virtual const char * getClassName ()
 Returns "CenterNeuron". More...

virtual void setActivationFunction (ActivationFunction f, ActivationFunction df)
virtual int getDimension ()
 The dimension of the center. More...


Protected Methods

virtual void _recacheOutput ()
 
See also:
Neuron::_recacheOutput.
More...


virtual void _recacheError ()
 
See also:
Neuron::_recacheError.
More...



Protected Attributes

real_center
 The center point. More...

int _dimension
 The dimension of the center point = the size of the input vector. More...

ActivationFunction _dActivationFunction

Detailed Description

A center-neuron, the building block of a Radial basis function network. Neurons of this type have a "center" which is a D-dimensional point in space, where D = the number of inputs taken by the neuron. The activation of this neuron is the euclidean distance between the input vector and the center point. The output of this neuron is typically the result of the gaussian distribution function applied to the activation
Todo:
Implement gradient-descent rule based updation of center-point


Constructor & Destructor Documentation

annie::CenterNeuron::CenterNeuron int    label,
int    dimension
 

Constructs a center with the given label and with the center point a random point in the given dimensional space.

Parameters:
label  The label to be given to the neuron
dimension  The dimension of the center-point = size of input vector

annie::CenterNeuron::CenterNeuron int    label,
VECTOR    center
 

Constructs a center with the given label and given center

Parameters:
label  The label to be given to the neuron
center  The center point

annie::CenterNeuron::CenterNeuron int    label,
int    dimension,
real    center[]
 

Constructs a center with the given label and given center

Parameters:
label  The label to be given to the neuron
dimension  The dimension of the center-point = size of input vector
center  The center point

virtual annie::CenterNeuron::~CenterNeuron   [virtual]
 


Member Function Documentation

virtual void annie::CenterNeuron::_recacheError   [protected, virtual]
 

See also:
Neuron::_recacheError.

Implements annie::Neuron.

virtual void annie::CenterNeuron::_recacheOutput   [protected, virtual]
 

See also:
Neuron::_recacheOutput.

Implements annie::Neuron.

virtual void annie::CenterNeuron::connect Neuron   from [virtual]
 

Sets the center-neuron to receive as input the output of the given neuron.

VECTOR annie::CenterNeuron::getCenter  
 

Returns the center point.

virtual const char* annie::CenterNeuron::getClassName   [virtual]
 

Returns "CenterNeuron".

Implements annie::Neuron.

virtual int annie::CenterNeuron::getDimension   [virtual]
 

The dimension of the center.

virtual void annie::CenterNeuron::setActivationFunction ActivationFunction    f,
ActivationFunction    df
[virtual]
 

Sets the activation function of the neuron and its derivative

Parameters:
f  The activation function to be used (gaussian by default)
df  The derivative of the activation function (dgaussian by default). Required for gradient descent training which is NOT YET IMPLEMENTED

virtual void annie::CenterNeuron::setCenter real    center[] [virtual]
 

Sets the center point.

virtual void annie::CenterNeuron::setCenter VECTOR    center [virtual]
 

Sets the center point.

virtual std::string annie::CenterNeuron::toString   [virtual]
 

See also:
Neuron::toString.

Reimplemented from annie::Neuron.


Member Data Documentation

real* annie::CenterNeuron::_center [protected]
 

The center point.

ActivationFunction annie::CenterNeuron::_dActivationFunction [protected]
 

Derivative of the activation function. Used for gradient descent rule based updation of weights and centers. Not yet implemented

int annie::CenterNeuron::_dimension [protected]
 

The dimension of the center point = the size of the input vector.


The documentation for this class was generated from the following file:
Generated on Wed Apr 23 10:42:36 2003 for BioFilter by doxygen1.2.14 written by Dimitri van Heesch, © 1997-2002