org.encog.neural.networks.logic
Class HopfieldLogic

java.lang.Object
  org.encog.neural.networks.logic.FeedforwardLogic
      org.encog.neural.networks.logic.SimpleRecurrentLogic
          org.encog.neural.networks.logic.ThermalLogic
              org.encog.neural.networks.logic.HopfieldLogic

All Implemented Interfaces:

java.io.Serializable, NeuralLogic

public class HopfieldLogic
extends ThermalLogic

Provides the neural logic for an Hopfield type network. See HopfieldPattern for more information on this type of network.

See Also:

Serialized Form

Constructor Summary

HopfieldLogic()

Method Summary

void	addPattern(NeuralData pattern) Train the neural network for the specified pattern.
void	run() Perform one Hopfield iteration.
int	runUntilStable(int max) Run the network until it becomes stable and does not change from more runs.

Methods inherited from class org.encog.neural.networks.logic.ThermalLogic

calculateEnergy, clear, getCurrentState, getNeuronCount, getThermalLayer, getThermalSynapse, init, setCurrentState

Methods inherited from class org.encog.neural.networks.logic.SimpleRecurrentLogic

preprocessLayer

Methods inherited from class org.encog.neural.networks.logic.FeedforwardLogic

compute, getNetwork

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

HopfieldLogic

public HopfieldLogic()

Method Detail

addPattern

public void addPattern(NeuralData pattern)

Train the neural network for the specified pattern. The neural network can be trained for more than one pattern. To do this simply call the train method more than once.

Parameters:

pattern - The pattern to train for.

run

public void run()

Perform one Hopfield iteration.

runUntilStable

public int runUntilStable(int max)

Run the network until it becomes stable and does not change from more runs.

Parameters:

max - The maximum number of cycles to run before giving up.

Returns:

The number of cycles that were run.