org.encog.neural.pattern
Class RadialBasisPattern

java.lang.Object
  extended by org.encog.neural.pattern.RadialBasisPattern
All Implemented Interfaces:
NeuralNetworkPattern

public class RadialBasisPattern
extends Object
implements NeuralNetworkPattern

A radial basis function (RBF) network uses several radial basis functions to provide a more dynamic hidden layer activation function than many other types of neural network. It consists of a input, output and hidden layer.

Author:
jheaton

Constructor Summary
RadialBasisPattern()
           
 
Method Summary
 void addHiddenLayer(int count)
          Add the hidden layer, this should be called once, as a RBF has a single hidden layer.
 void clear()
          Clear out any hidden neurons.
 MLMethod generate()
          Generate the RBF network.
 void setActivationFunction(ActivationFunction activation)
          Set the activation function, this is an error.
 void setInputNeurons(int count)
          Set the number of input neurons.
 void setOutputNeurons(int count)
          Set the number of output neurons.
 void setRBF(RBFEnum type)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

RadialBasisPattern

public RadialBasisPattern()
Method Detail

addHiddenLayer

public void addHiddenLayer(int count)
Add the hidden layer, this should be called once, as a RBF has a single hidden layer.

Specified by:
addHiddenLayer in interface NeuralNetworkPattern
Parameters:
count - The number of neurons in the hidden layer.

clear

public void clear()
Clear out any hidden neurons.

Specified by:
clear in interface NeuralNetworkPattern

generate

public MLMethod generate()
Generate the RBF network.

Specified by:
generate in interface NeuralNetworkPattern
Returns:
The neural network.

setActivationFunction

public void setActivationFunction(ActivationFunction activation)
Set the activation function, this is an error. The activation function may not be set on a RBF layer.

Specified by:
setActivationFunction in interface NeuralNetworkPattern
Parameters:
activation - The new activation function.

setInputNeurons

public void setInputNeurons(int count)
Set the number of input neurons.

Specified by:
setInputNeurons in interface NeuralNetworkPattern
Parameters:
count - The number of input neurons.

setOutputNeurons

public void setOutputNeurons(int count)
Set the number of output neurons.

Specified by:
setOutputNeurons in interface NeuralNetworkPattern
Parameters:
count - The number of output neurons.

setRBF

public void setRBF(RBFEnum type)


Copyright © 2014. All Rights Reserved.