org.encog.neural.thermal
Class ThermalNetwork

java.lang.Object
  extended by org.encog.ml.BasicML
      extended by org.encog.neural.thermal.ThermalNetwork
All Implemented Interfaces:
Serializable, MLAutoAssocation, MLInput, MLInputOutput, MLMethod, MLOutput, MLProperties, MLRegression, MLResettable
Direct Known Subclasses:
BoltzmannMachine, HopfieldNetwork

public abstract class ThermalNetwork
extends BasicML
implements MLMethod, MLAutoAssocation, MLResettable

The thermal network forms the base class for Hopfield and Boltzmann machines.

Author:
jheaton
See Also:
Serialized Form

Constructor Summary
ThermalNetwork()
          Default constructor.
ThermalNetwork(int neuronCount)
          Construct the network with the specicified neuron count.
 
Method Summary
 void addWeight(int fromNeuron, int toNeuron, double value)
          Add to the specified weight.
 double calculateEnergy()
           
 void clear()
          Clear any connection weights.
 BiPolarNeuralData getCurrentState()
           
 int getNeuronCount()
           
 double getWeight(int fromNeuron, int toNeuron)
          Get a weight.
 double[] getWeights()
           
 void init(int neuronCount, double[] weights, double[] output)
          Init the network.
 void reset()
          Reset the weights.
 void reset(int seed)
          Reset the weights with a seed.
 void setCurrentState(BiPolarNeuralData state)
           
 void setCurrentState(double[] s)
          Set the current state.
 void setNeuronCount(int c)
          Set the neuron count.
 void setWeight(int fromNeuron, int toNeuron, double value)
          Set the weight.
 void setWeights(double[] w)
          Set the weight array.
 
Methods inherited from class org.encog.ml.BasicML
getProperties, getPropertyDouble, getPropertyLong, getPropertyString, setProperty, setProperty, setProperty, updateProperties
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 
Methods inherited from interface org.encog.ml.MLRegression
compute
 
Methods inherited from interface org.encog.ml.MLInput
getInputCount
 
Methods inherited from interface org.encog.ml.MLOutput
getOutputCount
 

Constructor Detail

ThermalNetwork

public ThermalNetwork()
Default constructor.


ThermalNetwork

public ThermalNetwork(int neuronCount)
Construct the network with the specicified neuron count.

Parameters:
neuronCount - The number of neurons.
Method Detail

addWeight

public void addWeight(int fromNeuron,
                      int toNeuron,
                      double value)
Add to the specified weight.

Parameters:
fromNeuron - The from neuron.
toNeuron - The to neuron.
value - The value to add.

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.

getWeight

public double getWeight(int fromNeuron,
                        int toNeuron)
Get a weight.

Parameters:
fromNeuron - The from neuron.
toNeuron - The to neuron.
Returns:
The weight.

getWeights

public double[] getWeights()
Returns:
The weights.

init

public void init(int neuronCount,
                 double[] weights,
                 double[] output)
Init the network.

Parameters:
neuronCount - The neuron count.
weights - The weights.
output - The toutpu

reset

public void reset()
Reset the weights.

Specified by:
reset in interface MLResettable

reset

public void reset(int seed)
Reset the weights with a seed.

Specified by:
reset in interface MLResettable
Parameters:
seed - The seed value.

setCurrentState

public void setCurrentState(BiPolarNeuralData state)
Parameters:
state - The current state for the network.

setCurrentState

public void setCurrentState(double[] s)
Set the current state.

Parameters:
s - The current state array.

setNeuronCount

public void setNeuronCount(int c)
Set the neuron count.

Parameters:
c - The neuron count.

setWeight

public void setWeight(int fromNeuron,
                      int toNeuron,
                      double value)
Set the weight.

Parameters:
fromNeuron - The from neuron.
toNeuron - The to neuron.
value - The value.

setWeights

public void setWeights(double[] w)
Set the weight array.

Parameters:
w - The weight array.


Copyright © 2014. All Rights Reserved.