org.encog.neural.networks.logic
Class BoltzmannLogic

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.BoltzmannLogic

All Implemented Interfaces:

Serializable, NeuralLogic

public class BoltzmannLogic
extends ThermalLogic

Provides the neural logic for an Boltzmann type network. See BoltzmannPattern for more information on this type of network.

See Also:

Serialized Form

Field Summary

static String	PROPERTY_ANNEAL_CYCLES Neural network property, the number of annealing cycles to run.
static String	PROPERTY_RUN_CYCLES Neural network property, the number of cycles to run.
static String	PROPERTY_TEMPERATURE Neural network property, the temperature.

Constructor Summary

BoltzmannLogic()

Method Summary

NeuralData	compute(NeuralData input, NeuralOutputHolder useHolder) Setup the network logic, read parameters from the network.
void	decreaseTemperature(double d) Decrease the temperature by the specified amount.
void	establishEquilibrium() Run the network until thermal equilibrium is established.
double	getTemperature()
void	init(BasicNetwork network) Setup the network logic, read parameters from the network.
void	run() Run the network for all neurons present.
void	setTemperature(double temperature) Set the network temperature.

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

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

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

preprocessLayer

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

getNetwork

Methods inherited from class java.lang.Object

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

Field Detail

PROPERTY_RUN_CYCLES

public static final String PROPERTY_RUN_CYCLES

Neural network property, the number of cycles to run.

See Also:

Constant Field Values

PROPERTY_ANNEAL_CYCLES

public static final String PROPERTY_ANNEAL_CYCLES

Neural network property, the number of annealing cycles to run.

See Also:

Constant Field Values

PROPERTY_TEMPERATURE

public static final String PROPERTY_TEMPERATURE

Neural network property, the temperature.

See Also:

Constant Field Values

Constructor Detail

BoltzmannLogic

public BoltzmannLogic()

Method Detail

compute

public NeuralData compute(NeuralData input,
                          NeuralOutputHolder useHolder)

Setup the network logic, read parameters from the network. NOT USED, call the run method.

Specified by:

compute in interface NeuralLogic

Overrides:

compute in class FeedforwardLogic

Parameters:

input - NOT USED

useHolder - NOT USED

Returns:

NOT USED

decreaseTemperature

public void decreaseTemperature(double d)

Decrease the temperature by the specified amount.

Parameters:

d - The amount to decrease by.

establishEquilibrium

public void establishEquilibrium()

Run the network until thermal equilibrium is established.

getTemperature

public double getTemperature()

Returns:

The temperature the network is currently operating at.

init

public void init(BasicNetwork network)

Setup the network logic, read parameters from the network.

Specified by:

init in interface NeuralLogic

Overrides:

init in class ThermalLogic

Parameters:

network - The network that this logic class belongs to.

run

public void run()

Run the network for all neurons present.

setTemperature

public void setTemperature(double temperature)

Set the network temperature.

Parameters:

temperature - The temperature to operate the network at.