org.encog.neural.networks.logic
Class ThermalLogic

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

All Implemented Interfaces:

Serializable, NeuralLogic

Direct Known Subclasses:

BoltzmannLogic, HopfieldLogic

public class ThermalLogic
extends SimpleRecurrentLogic

Provides the neural logic for thermal networks. Functions as a base class for BoltzmannLogic and HopfieldLogic.

See Also:

Serialized Form

Constructor Summary

ThermalLogic()

Method Summary

double	calculateEnergy()
void	clear() Clear any connection weights.
BiPolarNeuralData	getCurrentState()
int	getNeuronCount()
Layer	getThermalLayer()
Synapse	getThermalSynapse()
void	init(BasicNetwork network) Setup the network logic, read parameters from the network.
void	setCurrentState(BiPolarNeuralData state)

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

ThermalLogic

public ThermalLogic()

Method Detail

calculateEnergy

public double calculateEnergy()

Returns:

Calculate the current energy for the network. The network will seek to lower this value.

clear

public void clear()

Clear any connection weights.

getCurrentState

public BiPolarNeuralData getCurrentState()

Returns:

The current state of the network.

getNeuronCount

public int getNeuronCount()

Returns:

Get the neuron count for the network.

getThermalLayer

public Layer getThermalLayer()

Returns:

The main thermal layer.

getThermalSynapse

public Synapse getThermalSynapse()

Returns:

The thermal synapse.

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 FeedforwardLogic

Parameters:

network - The network that this logic class belongs to.

setCurrentState

public void setCurrentState(BiPolarNeuralData state)

Parameters:

state - The current state for the network.