SigmoidalNeuron Class Reference
[Neural Network filtering]

SigmoidalNeuron implements the main functionality of neurons in a neural network. More...

#include <SigmoidalNeuron.h>

Inheritance diagram for SigmoidalNeuron:

Inheritance graph
[legend]

List of all members.

Public Types

enum  tneurontype { bipolar, identity }
 At the moment there are two types of neurons: bipolar and identity, they differ in their activation function. More...

Public Member Functions

virtual const std::vector
< double > & 
GetOldDelta ()
 Get the last weight correction for momentum adaptation.
virtual std::vector< double > & SetOldDelta ()
virtual double CalcDeriv (const double input)
 Return the derivative of the activation function.
virtual double GetNet ()
 Get the raw output of the linear combiner.
virtual double GetDelta ()
 Get the delta term of the weight correction formula.
virtual void SetDelta (const double d)
 Set the delta term of the weight correction formula.
virtual void SetBias (const double b)
 Set the bias of the linear combiner, the following functions are mostly for convenience access.
virtual double GetBias ()
 Get the bias of the linear combiner.
virtual const std::vector
< double > & 
GetWeights ()
 Get the weights.
virtual std::vector< double > & SetWeights ()
 Set the weights.
virtual const
GeneralLinearCombiner::tinvector
GetInput ()
 Get the input neurons.
virtual void SetInput (const GeneralLinearCombiner::tinvector &input)
 Set the input neurons.
virtual void SetType (tneurontype type)
 Set the type of neuron, determines the activation function.
 SigmoidalNeuron (tneurontype type, bool wantcached=false)
 Construct neuron with a known type.
virtual ~SigmoidalNeuron ()


Detailed Description

SigmoidalNeuron implements the main functionality of neurons in a neural network.

Definition at line 15 of file SigmoidalNeuron.h.


Member Enumeration Documentation

At the moment there are two types of neurons: bipolar and identity, they differ in their activation function.

Enumerator:
bipolar 
identity 

Definition at line 18 of file SigmoidalNeuron.h.


Constructor & Destructor Documentation

SigmoidalNeuron::SigmoidalNeuron ( tneurontype  type,
bool  wantcached = false 
) [explicit]

Construct neuron with a known type.

Definition at line 6 of file SigmoidalNeuron.cpp.

References SetType().

SigmoidalNeuron::~SigmoidalNeuron (  )  [virtual]

Definition at line 15 of file SigmoidalNeuron.cpp.


Member Function Documentation

virtual double SigmoidalNeuron::CalcDeriv ( const double  input  )  [inline, virtual]

Return the derivative of the activation function.

Implements GeneralNeuron.

Definition at line 41 of file SigmoidalNeuron.h.

virtual double SigmoidalNeuron::GetBias (  )  [inline, virtual]

Get the bias of the linear combiner.

Implements GeneralNeuron.

Definition at line 51 of file SigmoidalNeuron.h.

virtual double SigmoidalNeuron::GetDelta (  )  [inline, virtual]

Get the delta term of the weight correction formula.

Implements GeneralNeuron.

Definition at line 45 of file SigmoidalNeuron.h.

virtual const GeneralLinearCombiner::tinvector& SigmoidalNeuron::GetInput (  )  [inline, virtual]

Get the input neurons.

Implements GeneralNeuron.

Definition at line 57 of file SigmoidalNeuron.h.

virtual double SigmoidalNeuron::GetNet (  )  [inline, virtual]

Get the raw output of the linear combiner.

Implements GeneralNeuron.

Definition at line 43 of file SigmoidalNeuron.h.

virtual const std::vector<double>& SigmoidalNeuron::GetOldDelta (  )  [inline, virtual]

Get the last weight correction for momentum adaptation.

Implements GeneralNeuron.

Definition at line 38 of file SigmoidalNeuron.h.

virtual const std::vector<double>& SigmoidalNeuron::GetWeights (  )  [inline, virtual]

Get the weights.

Implements GeneralNeuron.

Definition at line 53 of file SigmoidalNeuron.h.

virtual void SigmoidalNeuron::SetBias ( const double  b  )  [inline, virtual]

Set the bias of the linear combiner, the following functions are mostly for convenience access.

Implements GeneralNeuron.

Definition at line 49 of file SigmoidalNeuron.h.

virtual void SigmoidalNeuron::SetDelta ( const double  d  )  [inline, virtual]

Set the delta term of the weight correction formula.

Implements GeneralNeuron.

Definition at line 47 of file SigmoidalNeuron.h.

void SigmoidalNeuron::SetInput ( const GeneralLinearCombiner::tinvector input  )  [virtual]

Set the input neurons.

Reimplemented from GeneralNeuron.

Definition at line 26 of file SigmoidalNeuron.cpp.

virtual std::vector<double>& SigmoidalNeuron::SetOldDelta (  )  [inline, virtual]

Implements GeneralNeuron.

Definition at line 39 of file SigmoidalNeuron.h.

void SigmoidalNeuron::SetType ( tneurontype  type  )  [virtual]

Set the type of neuron, determines the activation function.

Definition at line 32 of file SigmoidalNeuron.cpp.

References bipolar, and identity.

Referenced by SigmoidalNeuron().

virtual std::vector<double>& SigmoidalNeuron::SetWeights (  )  [inline, virtual]

Set the weights.

Implements GeneralNeuron.

Definition at line 55 of file SigmoidalNeuron.h.


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

Generated on Tue Aug 4 16:04:22 2009 for GPLIB++ by  doxygen 1.5.8