objectives

Type Members

1. class BinaryCrossEntropy[T] extends TensorLossFunction[T]

   

   This loss function measures the Binary Cross Entropy between the target and the output loss(o, t) = - 1/n sum_i (t[i] * log(o[i]) + (1 - t[i]) * log(1 - o[i])) or in the case of the weights argument being specified: loss(o, t) = - 1/n sum_i weights[i] * (t[i] * log(o[i]) + (1 - t[i]) * log(1 - o[i]))

2. class CategoricalCrossEntropy[T] extends TensorLossFunction[T]

   

   This is same with cross entropy criterion except the target tensor is a one-hot tensor

3. class CosineProximity[T] extends TensorLossFunction[T]

   

   The negative of the mean cosine proximity between predictions and targets.

   The negative of the mean cosine proximity between predictions and targets. The cosine proximity is defined as below: x'(i) = x(i) / sqrt(max(sum(x(i)^{2), 1e-12)) y'(i) = y(i) / sqrt(max(sum(x(i)}2), 1e-12)) cosine_proximity(x, y) = mean(-1 * x'(i) * y'(i))

4. class Hinge[T] extends TensorLossFunction[T]

   

   Creates a criterion that optimizes a two-class classification hinge loss (margin-based loss) between input x (a Tensor of dimension 1) and output y.

5. class KullbackLeiblerDivergence[T] extends TensorLossFunction[T]

   

   Loss calculated as: y_true = K.clip(y_true, K.epsilon(), 1) y_pred = K.clip(y_pred, K.epsilon(), 1) and output K.sum(y_true * K.log(y_true / y_pred), axis=-1)

6. abstract class LossFunction[A <: Activity, B <: Activity, T] extends AbstractCriterion[A, B, T]

   

   The base class for Keras-style API objectives in Analytics Zoo.

   The base class for Keras-style API objectives in Analytics Zoo.

   A

   Input data type.

   B

   Target data type.

7. class MeanAbsoluteError[T] extends TensorLossFunction[T]

   

   A loss that measures the mean absolute value of the element-wise difference between the input and the target.

8. class MeanAbsolutePercentageError[T] extends TensorLossFunction[T]

   

   It caculates diff = K.abs((y - x) / K.clip(K.abs(y), K.epsilon(), Double.MaxValue)) and return 100 * K.mean(diff) as outpout

9. class MeanSquaredError[T] extends TensorLossFunction[T]

   

   The mean squared error criterion e.g.

   The mean squared error criterion e.g. input: a, target: b, total elements: n loss(a, b) = 1/n \sum |a_i - b_i|^2

10. class MeanSquaredLogarithmicError[T] extends TensorLossFunction[T]

    

    It calculates: first_log = K.log(K.clip(y, K.epsilon(), Double.MaxValue) + 1.) second_log = K.log(K.clip(x, K.epsilon(), Double.MaxValue) + 1.) and output K.mean(K.square(first_log - second_log))

11. class Poisson[T] extends TensorLossFunction[T]

    

    Loss calculated as: K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)

12. class RankHinge[T] extends TensorLossFunction[T]

    

    Hinge loss for pairwise ranking problems.

13. class SparseCategoricalCrossEntropy[T] extends TensorLossFunction[T]

    

    A loss often used in multi-class classification problems with SoftMax as the last layer of the neural network.

    A loss often used in multi-class classification problems with SoftMax as the last layer of the neural network.

    By default, input(y_pred) is supposed to be probabilities of each class, and target(y_true) is supposed to be the class label starting from 0.

14. class SquaredHinge[T] extends TensorLossFunction[T]

    

    Creates a criterion that optimizes a two-class classification squared hinge loss (margin-based loss) between input x (a Tensor of dimension 1) and output y.

15. abstract class TensorLossFunction[T] extends LossFunction[Tensor[T], Tensor[T], T]

    

    A subclass of LossFunction where input and target are both Tensors.