Package de.jungblut.math.loss

Interface Summary

Interface	Description
LossFunction	Calculates the error, for example in the last layer of a neural net.

Class Summary

Class	Description
CrossEntropyLoss	Cross entropy error function, for example to be used with the SoftMaxActivationFunction.
HingeLoss	Hinge-loss for linear SVMs.
LogLoss	Logistic error function implementation.
MeanAbsoluteLoss	MAE for regression problems.
SquaredLoss	Squared mean error function for regression problems and LinearActivationFunction.
StepLoss	Calculates a step error function that can be used for StepActivationFunction.