A.I.M.S algorithms


AimsMLPLayer Class Reference

The class to manage MLP layers of neurons. More...

#include <aims/neuralnet/multilayerperceptron.h>

Collaboration diagram for AimsMLPLayer:

Public Member Functions

Constructor and Destructor
 AimsMLPLayer (int nneurons, int ninputs)
 Two arguments must be given to the constructor. More...
 
virtual ~AimsMLPLayer ()
 Destructor deletes the pointer of neuron pointers. More...
 
Methods
int nNeurons () const
 Return the number of neurons in the layer. More...
 
AimsData< float > activations () const
 Return the vector of activations. More...
 
AimsData< float > outputs () const
 Return the vector of outputs. More...
 
AimsData< float > errors () const
 Return the vector of errors. More...
 
AimsData< float > nextWeights (int n) const
 Return the weights coming from input n. More...
 
void setWeight (const AimsData< float > &weight, int neuron)
 Set the weights of a specific neuron of the layer. More...
 
void forward (const AimsData< float > &input)
 Forward propagation on the layer. More...
 
float evaluateError (const AimsData< float > &target)
 Evaluation of the error of the layer for a given target. More...
 
void backPropagation (const AimsMLPLayer &nextlayer)
 Gradient back propagation on the layer. More...
 
void adjust (const AimsData< float > &input, float learningrate, float momentum)
 Modification of the weights. More...
 

Protected Attributes

Data
int _nNeurons
 Number of neurons. More...
 
AimsMLPNeuron ** _neuron
 Pointer to neuron pointers. More...
 

Detailed Description

The class to manage MLP layers of neurons.

Definition at line 110 of file multilayerperceptron.h.

Constructor & Destructor Documentation

AimsMLPLayer::AimsMLPLayer ( int  nneurons,
int  ninputs 
)

Two arguments must be given to the constructor.

Parameters
nneuronsnumber of neurons in the layer
ninputsnumber of inputs on each neuron
virtual AimsMLPLayer::~AimsMLPLayer ( )
virtual

Destructor deletes the pointer of neuron pointers.

Member Function Documentation

AimsData<float> AimsMLPLayer::activations ( ) const

Return the vector of activations.

void AimsMLPLayer::adjust ( const AimsData< float > &  input,
float  learningrate,
float  momentum 
)

Modification of the weights.

void AimsMLPLayer::backPropagation ( const AimsMLPLayer nextlayer)

Gradient back propagation on the layer.

AimsData<float> AimsMLPLayer::errors ( ) const

Return the vector of errors.

float AimsMLPLayer::evaluateError ( const AimsData< float > &  target)

Evaluation of the error of the layer for a given target.

void AimsMLPLayer::forward ( const AimsData< float > &  input)

Forward propagation on the layer.

AimsData<float> AimsMLPLayer::nextWeights ( int  n) const

Return the weights coming from input n.

int AimsMLPLayer::nNeurons ( ) const

Return the number of neurons in the layer.

AimsData<float> AimsMLPLayer::outputs ( ) const

Return the vector of outputs.

void AimsMLPLayer::setWeight ( const AimsData< float > &  weight,
int  neuron 
)

Set the weights of a specific neuron of the layer.

Member Data Documentation

AimsMLPNeuron** AimsMLPLayer::_neuron
protected

Pointer to neuron pointers.

Definition at line 117 of file multilayerperceptron.h.

int AimsMLPLayer::_nNeurons
protected

Number of neurons.

Definition at line 115 of file multilayerperceptron.h.


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