Uses of Class
org.nd4j.autodiff.loss.LossFunctions.Reduction

Packages that use LossFunctions.Reduction

Package	Description
org.nd4j.autodiff.loss

Uses of LossFunctions.Reduction in org.nd4j.autodiff.loss

Methods in org.nd4j.autodiff.loss that return LossFunctions.Reduction

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

Methods in org.nd4j.autodiff.loss with parameters of type LossFunctions.Reduction

Modifier and Type	Method and Description
static LossInfo	LossFunctions.l1(String outputName, SDVariable predictions, SDVariable label, SDVariable weights, LossFunctions.Reduction reduction, int... dimensions) L1 loss - sum of absolute errors.
static LossInfo	LossFunctions.l2(String outputName, SDVariable predictions, SDVariable label, SDVariable weights, LossFunctions.Reduction reduction, int... dimensions) L2 loss function: i.e., sum of squared errors, L = sum_i (actual_i - predicted)^2
static LossInfo	LossFunctions.mcxent(String outputName, SDVariable predictions, SDVariable label, SDVariable weights, LossFunctions.Reduction reduction, int... dimensions) Multi-Class Cross Entropy loss function: L = sum_i actual_i * log( predicted_i )
static LossInfo	LossFunctions.mse(String outputName, SDVariable predictions, SDVariable label, SDVariable weights, LossFunctions.Reduction reduction, int... dimensions) Mean squared error: L = mean( (predicted - label)^2)
static LossInfo	LossFunctions.negativeLogLikelihood(String outputName, SDVariable predictions, SDVariable label, SDVariable weights, LossFunctions.Reduction reduction, int... dimensions)