org.encog.neural.networks.training.strategy
Class RegularizationStrategy

java.lang.Object
  extended by org.encog.neural.networks.training.strategy.RegularizationStrategy
All Implemented Interfaces:
Strategy

public class RegularizationStrategy
extends Object
implements Strategy


Constructor Summary
RegularizationStrategy(double lambda)
           
 
Method Summary
 void init(MLTrain train)
          Initialize this strategy.
 void postIteration()
          Called just after a training iteration.
 void preIteration()
          Called just before a training iteration.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

RegularizationStrategy

public RegularizationStrategy(double lambda)
Method Detail

init

public void init(MLTrain train)
Description copied from interface: Strategy
Initialize this strategy.

Specified by:
init in interface Strategy
Parameters:
train - The training algorithm.

preIteration

public void preIteration()
Description copied from interface: Strategy
Called just before a training iteration.

Specified by:
preIteration in interface Strategy

postIteration

public void postIteration()
Description copied from interface: Strategy
Called just after a training iteration.

Specified by:
postIteration in interface Strategy


Copyright © 2014. All Rights Reserved.