MLCLossLayer
A layer that estimates the inaccuracies of the model to reduce the loss on the next evaluation.
Declaration
class MLCLossLayerTopics
Creating Loss Layers with Descriptors
Creating Loss Layers with Scalar Weights
softmaxCrossEntropy(reductionType:labelSmoothing:classCount:weight:)categoricalCrossEntropy(reductionType:labelSmoothing:classCount:weight:)sigmoidCrossEntropy(reductionType:labelSmoothing:weight:)log(reductionType:epsilon:weight:)huberLoss(reductionType:delta:weight:)meanAbsoluteError(reductionType:weight:)meanSquaredError(reductionType:weight:)hingeLoss(reductionType:weight:)cosineDistance(reductionType:weight:)
Creating Loss Layers with Tensor Weights
softmaxCrossEntropy(reductionType:labelSmoothing:classCount:weights:)categoricalCrossEntropy(reductionType:labelSmoothing:classCount:weights:)sigmoidCrossEntropy(reductionType:labelSmoothing:weights:)log(reductionType:epsilon:weights:)huberLoss(reductionType:delta:weights:)meanAbsoluteError(reductionType:weights:)meanSquaredError(reductionType:weights:)hingeLoss(reductionType:weights:)cosineDistance(reductionType:weights:)