org.encog.neural.networks.training.cross
Class NetworkFold

java.lang.Object
  extended by org.encog.neural.networks.training.cross.NetworkFold

public class NetworkFold
extends Object

The network for one fold of a cross validation.


Constructor Summary
NetworkFold(FlatNetwork flat)
          Construct a fold from the specified flat network.
 
Method Summary
 void copyFromNetwork(FlatNetwork source)
          Copy the weights and output from the network.
 void copyToNetwork(FlatNetwork target)
          Copy weights and output to the network.
 double[] getOutput()
           
 double[] getWeights()
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

NetworkFold

public NetworkFold(FlatNetwork flat)
Construct a fold from the specified flat network.

Parameters:
flat - THe flat network.
Method Detail

copyToNetwork

public final void copyToNetwork(FlatNetwork target)
Copy weights and output to the network.

Parameters:
target - The network to copy to.

copyFromNetwork

public final void copyFromNetwork(FlatNetwork source)
Copy the weights and output from the network.

Parameters:
source - The network to copy from.

getWeights

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

getOutput

public final double[] getOutput()
Returns:
The network output.


Copyright © 2014. All Rights Reserved.