org.nd4j.autodiff.loss

Enum LossReduce

java.lang.Object

java.lang.Enum<LossReduce>

org.nd4j.autodiff.loss.LossReduce

All Implemented Interfaces:

Serializable, Comparable<LossReduce>

public enum LossReduce
extends Enum<LossReduce>

The LossReduce enum specifies how (or if) the values of a loss function should be reduced to a single value. See the javadoc comments on the individual enumeration constants for details.

Author:

Alex Black

Enum Constant Summary

Enum Constants

Enum Constant and Description
MEAN_BY_NONZERO_WEIGHT_COUNT Weighted mean: sum(weights * perOutputLoss) / count(weights != 0) Example: 2d input, mean squared error loss. Output: squared_error_per_ex = weights * squaredDifference(predictions,labels) output = sum(squared_error_per_ex) / count(weights != 0) NOTE: if weights array is not provided, then weights default to scalar 1.0 and hence MEAN_BY_NONZERO_WEIGHT_COUNT is equivalent to MEAN_BY_WEIGHT
MEAN_BY_WEIGHT Weighted mean: sum(weights * perOutputLoss) / sum(weights) - gives a single scalar output Example: 2d input, mean squared error Output: squared_error_per_ex = weights * squaredDifference(predictions,labels) output = sum(squared_error_per_ex) / sum(weights) NOTE: if weights array is not provided, then weights default to 1.0 for all entries - and hence MEAN_BY_WEIGHT is equivalent to MEAN_BY_NONZERO_WEIGHT_COUNT
NONE No reduction.
SUM Weigted sum across all loss values, returning a scalar.

Method Summary

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

Methods inherited from class java.lang.Enum

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

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Detail

NONE

public static final LossReduce NONE

No reduction. In most cases, output is the same shape as the predictions/labels.
Weights (if any) are applied
Example Input: 2d input array with mean squared error loss.
Example Output: squaredDifference(predictions,labels), with same shape as input/labels

SUM

public static final LossReduce SUM

Weigted sum across all loss values, returning a scalar.

MEAN_BY_WEIGHT

public static final LossReduce MEAN_BY_WEIGHT

Weighted mean: sum(weights * perOutputLoss) / sum(weights) - gives a single scalar output
Example: 2d input, mean squared error
Output: squared_error_per_ex = weights * squaredDifference(predictions,labels)
output = sum(squared_error_per_ex) / sum(weights)

NOTE: if weights array is not provided, then weights default to 1.0 for all entries - and hence MEAN_BY_WEIGHT is equivalent to MEAN_BY_NONZERO_WEIGHT_COUNT

MEAN_BY_NONZERO_WEIGHT_COUNT

public static final LossReduce MEAN_BY_NONZERO_WEIGHT_COUNT

Weighted mean: sum(weights * perOutputLoss) / count(weights != 0)
Example: 2d input, mean squared error loss.
Output: squared_error_per_ex = weights * squaredDifference(predictions,labels)
output = sum(squared_error_per_ex) / count(weights != 0)
NOTE: if weights array is not provided, then weights default to scalar 1.0 and hence MEAN_BY_NONZERO_WEIGHT_COUNT is equivalent to MEAN_BY_WEIGHT

Method Detail

values

public static LossReduce[] values()

Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows:

for (LossReduce c : LossReduce.values())
    System.out.println(c);

Returns:

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

valueOf

public static LossReduce valueOf(String name)

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (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 type has no constant with the specified name

NullPointerException - if the argument is null