org.encog.neural.thermal
Class BoltzmannMachine

java.lang.Object
  org.encog.ml.BasicML
      org.encog.neural.thermal.ThermalNetwork
          org.encog.neural.thermal.BoltzmannMachine

All Implemented Interfaces:

Serializable, MLAutoAssocation, MLInput, MLInputOutput, MLMethod, MLOutput, MLProperties, MLRegression, MLResettable

public class BoltzmannMachine
extends ThermalNetwork

Implements a Boltzmann machine.

See Also:

Serialized Form

Field Summary

static String	ANNEAL_CYCLES The property for anneal cycles.
static String	RUN_CYCLES The property for run cycles.

Constructor Summary

BoltzmannMachine()
Default constructors.

BoltzmannMachine(int neuronCount)
Construct a Boltzmann machine with the specified number of neurons.

Method Summary

MLData	compute(MLData input) Note: for Boltzmann networks, you will usually want to call the "run" method to compute the output.
void	decreaseTemperature(double d) Decrease the temperature by the specified amount.
void	establishEquilibrium() Run the network until thermal equilibrium is established.
int	getAnnealCycles()
int	getInputCount()
int	getOutputCount()
int	getRunCycles()
double	getTemperature()
double[]	getThreshold()
void	run() Run the network for all neurons present.
void	run(int i) Run the network for the specified neuron.
void	setAnnealCycles(int annealCycles)
void	setRunCycles(int runCycles)
void	setTemperature(double temperature) Set the network temperature.
void	setThreshold(double[] t) Set the thresholds.
void	updateProperties() Update any objeccts when a property changes.

Methods inherited from class org.encog.neural.thermal.ThermalNetwork

addWeight, calculateEnergy, clear, getCurrentState, getNeuronCount, getWeight, getWeights, init, reset, reset, setCurrentState, setCurrentState, setNeuronCount, setWeight, setWeights

Methods inherited from class org.encog.ml.BasicML

getProperties, getPropertyDouble, getPropertyLong, getPropertyString, setProperty, setProperty, setProperty

Methods inherited from class java.lang.Object

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

Field Detail

RUN_CYCLES

public static final String RUN_CYCLES

The property for run cycles.

See Also:

Constant Field Values

ANNEAL_CYCLES

public static final String ANNEAL_CYCLES

The property for anneal cycles.

See Also:

Constant Field Values

Constructor Detail

BoltzmannMachine

public BoltzmannMachine()

Default constructors.

BoltzmannMachine

public BoltzmannMachine(int neuronCount)

Construct a Boltzmann machine with the specified number of neurons.

Parameters:

neuronCount - The number of neurons.

Method Detail

compute

public MLData compute(MLData input)

Note: for Boltzmann networks, you will usually want to call the "run" method to compute the output. This method can be used to copy the input data to the current state. A single iteration is then run, and the new current state is returned.

Parameters:

input - The input pattern.

Returns:

The new current state.

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.

getAnnealCycles

public int getAnnealCycles()

Returns:

the annealCycles

getInputCount

public int getInputCount()

Returns:

The input.

getOutputCount

public int getOutputCount()

Returns:

The output count.

getRunCycles

public int getRunCycles()

Returns:

the runCycles

getTemperature

public double getTemperature()

Returns:

The temperature the network is currently operating at.

getThreshold

public double[] getThreshold()

Returns:

the threshold

run

public void run()

Run the network for all neurons present.

run

public void run(int i)

Run the network for the specified neuron.

Parameters:

i - The neuron to run for.

setAnnealCycles

public void setAnnealCycles(int annealCycles)

Parameters:

annealCycles - the annealCycles to set

setRunCycles

public void setRunCycles(int runCycles)

Parameters:

runCycles - the runCycles to set

setTemperature

public void setTemperature(double temperature)

Set the network temperature.

Parameters:

temperature - The temperature to operate the network at.

setThreshold

public void setThreshold(double[] t)

Set the thresholds.

Parameters:

t - The thresholds.

updateProperties

public void updateProperties()

Update any objeccts when a property changes.

Specified by:

updateProperties in interface MLProperties

Specified by:

updateProperties in class BasicML