Package org.nd4j.linalg.api.ops.impl.loss.bp

Class Summary

Class	Description
AbsoluteDifferenceLossBp	Absolute difference loss backprop
BaseLossBp
CosineDistanceLossBp	Cosine distance loss
HingeLossBp	Hinge loss
HuberLossBp	Hinge loss
LogLossBp	Binary log loss, or cross entropy loss: -1/numExamples * sum_i (labels[i] * log(predictions[i] + epsilon) + (1-labels[i]) * log(1-predictions[i] + epsilon))
LogPoissonLossBp	Log Poisson loss backprop
MeanPairwiseSquaredErrorLossBp	Mean Pairwise Squared Error Loss Backprop
MeanSquaredErrorLossBp	Mean squared error loss
SigmoidCrossEntropyLossBp	Sigmoid cross entropy loss with logits
SoftmaxCrossEntropyLossBp	Softmax cross entropy loss
SoftmaxCrossEntropyWithLogitsLossBp	Softmax cross entropy loss with Logits
SparseSoftmaxCrossEntropyLossWithLogitsBp	Sparse softmax cross entropy loss with logits.