Computes the squared hinge loss between y_true & y_pred.

Formula:

loss <- square(maximum(1 - y_true * y_pred, 0))

y_true values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1.

Usage

loss_squared_hinge(
  y_true,
  y_pred,
  ...,
  reduction = "sum_over_batch_size",
  name = "squared_hinge",
  dtype = NULL
)

y_true: The ground truth values. y_true values are expected to be -1 or 1. If binary (0 or 1) labels are provided we will convert them to -1 or 1 with shape = [batch_size, d0, .. dN].
y_pred: The predicted values with shape = [batch_size, d0, .. dN].
...: For forward/backward compatability.
reduction: Type of reduction to apply to the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size", "mean", "mean_with_sample_weight" or NULL. "sum" sums the loss, "sum_over_batch_size" and "mean" sum the loss and divide by the sample size, and "mean_with_sample_weight" sums the loss and divides by the sum of the sample weights. "none" and NULL perform no aggregation. Defaults to "sum_over_batch_size".
name: Optional name for the loss instance.
dtype: The dtype of the loss's computations. Defaults to NULL, which means using config_floatx(). config_floatx() is a "float32" unless set to different value (via config_set_floatx()). If a keras$DTypePolicy is provided, then the compute_dtype will be utilized.

Squared hinge loss values with shape = [batch_size, d0, .. dN-1].

y_true <- array(sample(c(-1,1), 6, replace = TRUE), dim = c(2, 3))
y_pred <- random_uniform(c(2, 3))
loss <- loss_squared_hinge(y_true, y_pred)