org.encog.ml.train.strategy
Class StopTrainingStrategy

java.lang.Object
  extended by org.encog.ml.train.strategy.StopTrainingStrategy
All Implemented Interfaces:
EndTrainingStrategy, Strategy

public class StopTrainingStrategy
extends Object
implements EndTrainingStrategy

This strategy will indicate once training is no longer improving the neural network by a specified amount, over a specified number of cycles. This allows the program to automatically determine when to stop training.

Author:
jheaton

Field Summary
static double DEFAULT_MIN_IMPROVEMENT
          The default minimum improvement before training stops.
static int DEFAULT_TOLERATE_CYCLES
          The default number of cycles to tolerate.
 
Constructor Summary
StopTrainingStrategy()
          Construct the strategy with default options.
StopTrainingStrategy(double minImprovement, int toleratedCycles)
          Construct the strategy with the specified parameters.
 
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.
 boolean shouldStop()
          
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

DEFAULT_MIN_IMPROVEMENT

public static final double DEFAULT_MIN_IMPROVEMENT
The default minimum improvement before training stops.

See Also:
Constant Field Values

DEFAULT_TOLERATE_CYCLES

public static final int DEFAULT_TOLERATE_CYCLES
The default number of cycles to tolerate.

See Also:
Constant Field Values
Constructor Detail

StopTrainingStrategy

public StopTrainingStrategy()
Construct the strategy with default options.


StopTrainingStrategy

public StopTrainingStrategy(double minImprovement,
                            int toleratedCycles)
Construct the strategy with the specified parameters.

Parameters:
minImprovement - The minimum accepted improvement.
toleratedCycles - The number of cycles to tolerate before stopping.
Method Detail

init

public void init(MLTrain train)
Initialize this strategy.

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

postIteration

public void postIteration()
Called just after a training iteration.

Specified by:
postIteration in interface Strategy

preIteration

public void preIteration()
Called just before a training iteration.

Specified by:
preIteration in interface Strategy

shouldStop

public boolean shouldStop()

Specified by:
shouldStop in interface EndTrainingStrategy
Returns:
True if training should stop.


Copyright © 2014. All Rights Reserved.