Package si.ijs.kt.clus.main.settings.section

Enum Class SettingsRules.OptimizationGDMTCombineGradient

java.lang.Object

java.lang.Enum<SettingsRules.OptimizationGDMTCombineGradient>

si.ijs.kt.clus.main.settings.section.SettingsRules.OptimizationGDMTCombineGradient

All Implemented Interfaces:

Serializable, Comparable<SettingsRules.OptimizationGDMTCombineGradient>, java.lang.constant.Constable

Enclosing class:

SettingsRules

public static enum SettingsRules.OptimizationGDMTCombineGradient
extends Enum<SettingsRules.OptimizationGDMTCombineGradient>

GD optimization. Possible values for combining gradient targets to single gradient value.

Nested Class Summary

Nested classes/interfaces inherited from class java.lang.Enum

Enum.EnumDesc<E extends Enum<E>>

Enum Constant Summary

Enum Constants

Enum Constant	Description
Avg	GD optimization, combining of targets - combine by taking average.
Max	GD optimization, combining of targets - combine by taking max gradient.
MaxLoss	GD optimization, combining of targets - combine by taking the gradient of target with maximal loss.
MaxLossFast	GD optimization, combining of targets - combine by taking the gradient of target with maximal LINEAR loss.

Method Summary

Modifier and Type	Method	Description
static SettingsRules.OptimizationGDMTCombineGradient	valueOf(String name)	Returns the enum constant of this class with the specified name.
static SettingsRules.OptimizationGDMTCombineGradient[]	values()	Returns an array containing the constants of this enum class, in the order they are declared.

Methods inherited from class java.lang.Enum

clone, compareTo, describeConstable, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Details

Avg

public static final SettingsRules.OptimizationGDMTCombineGradient Avg

GD optimization, combining of targets - combine by taking average.

Max

public static final SettingsRules.OptimizationGDMTCombineGradient Max

GD optimization, combining of targets - combine by taking max gradient.

MaxLoss

public static final SettingsRules.OptimizationGDMTCombineGradient MaxLoss

GD optimization, combining of targets - combine by taking the gradient of target with maximal loss.

MaxLossFast

public static final SettingsRules.OptimizationGDMTCombineGradient MaxLossFast

GD optimization, combining of targets - combine by taking the gradient of target with maximal LINEAR loss. I.e. if the real loss is something else, we still use linear loss. NOT IMPLEMENTED! In fact was not any faster AND max loss is worse than avg.

Method Details

values

public static SettingsRules.OptimizationGDMTCombineGradient[] values()

Returns an array containing the constants of this enum class, in the order they are declared.

Returns:

an array containing the constants of this enum class, in the order they are declared

valueOf

public static SettingsRules.OptimizationGDMTCombineGradient valueOf(String name)

Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum class has no constant with the specified name

NullPointerException - if the argument is null