org.encog.neural.networks.training.propagation.resilient
Class RPROPConst

java.lang.Object
  extended by org.encog.neural.networks.training.propagation.resilient.RPROPConst

public final class RPROPConst
extends Object

Constants used for Resilient Propagation (RPROP) training.


Field Summary
static double DEFAULT_INITIAL_UPDATE
          The starting update for a delta.
static double DEFAULT_MAX_STEP
          The maximum amount a delta can reach.
static double DEFAULT_ZERO_TOLERANCE
          The default zero tolerance.
static double DELTA_MIN
          The minimum delta value for a weight matrix value.
static double NEGATIVE_ETA
          The NEGATIVE ETA value.
static double POSITIVE_ETA
          The POSITIVE ETA value.
 
Method Summary
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

DEFAULT_ZERO_TOLERANCE

public static final double DEFAULT_ZERO_TOLERANCE
The default zero tolerance.

See Also:
Constant Field Values

POSITIVE_ETA

public static final double POSITIVE_ETA
The POSITIVE ETA value. This is specified by the resilient propagation algorithm. This is the percentage by which the deltas are increased by if the partial derivative is greater than zero.

See Also:
Constant Field Values

NEGATIVE_ETA

public static final double NEGATIVE_ETA
The NEGATIVE ETA value. This is specified by the resilient propagation algorithm. This is the percentage by which the deltas are increased by if the partial derivative is less than zero.

See Also:
Constant Field Values

DELTA_MIN

public static final double DELTA_MIN
The minimum delta value for a weight matrix value.

See Also:
Constant Field Values

DEFAULT_INITIAL_UPDATE

public static final double DEFAULT_INITIAL_UPDATE
The starting update for a delta.

See Also:
Constant Field Values

DEFAULT_MAX_STEP

public static final double DEFAULT_MAX_STEP
The maximum amount a delta can reach.

See Also:
Constant Field Values


Copyright © 2014. All Rights Reserved.