org.encog.neural.pattern
Class HopfieldPattern

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

public class HopfieldPattern
extends Object
implements NeuralNetworkPattern

Create a Hopfield pattern. A Hopfield neural network has a single layer that functions both as the input and output layers. There are no hidden layers. Hopfield networks are used for basic pattern recognition. When a Hopfield network recognizes a pattern, it "echos" that pattern on the output.

Author:
jheaton

Constructor Summary
HopfieldPattern()
           
 
Method Summary
 void addHiddenLayer(int count)
          Add a hidden layer.
 void clear()
          Nothing to clear.
 MLMethod generate()
          Generate the Hopfield neural network.
 void setActivationFunction(ActivationFunction activation)
          Set the activation function to use.
 void setInputNeurons(int count)
          Set the number of input neurons, this must match the output neurons.
 void setOutputNeurons(int count)
          Set the number of output neurons, should not be used with a hopfield neural network, because the number of input neurons defines the number of output neurons.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

HopfieldPattern

public HopfieldPattern()
Method Detail

addHiddenLayer

public void addHiddenLayer(int count)
Add a hidden layer. This will throw an error, because the Hopfield neural network has no hidden layers.

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

clear

public void clear()
Nothing to clear.

Specified by:
clear in interface NeuralNetworkPattern

generate

public MLMethod generate()
Generate the Hopfield neural network.

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

setActivationFunction

public void setActivationFunction(ActivationFunction activation)
Set the activation function to use. This function will throw an error, because the Hopfield network must use the BiPolar activation function.

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

setInputNeurons

public void setInputNeurons(int count)
Set the number of input neurons, this must match the output neurons.

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

setOutputNeurons

public void setOutputNeurons(int count)
Set the number of output neurons, should not be used with a hopfield neural network, because the number of input neurons defines the number of output neurons.

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


Copyright © 2014. All Rights Reserved.