SupervisedLoss

interfacein packageklyn.math.nn.losses

public interface SupervisedLoss<T extends AbstractFloat = Float, Targets extends AbstractNumber = Int>

SupervisedLoss

Typed mean supervised objective. Target storage is part of the contract: integer class indices and floating regression values are not interchangeable.

Example

loss as SupervisedLoss<Float, Float> = MeanSquaredError<Float>()

Methods

Modifier and Type	Member	Description
public	compute `compute(outputs as NDArray<T>, targets as NDArray<Targets>, gradientScale as Double = 1.0) as LossResult<T>`	Computes mean loss and its derivative without changing either input.