loss_mean_squared_error: Computes the mean of squares of errors between labels and...
In rstudio/keras: R Interface to 'Keras'

loss_mean_squared_error

R Documentation

Computes the mean of squares of errors between labels and predictions.

Description

Formula:

loss <- mean(square(y_true - y_pred))

Usage

loss_mean_squared_error(
  y_true,
  y_pred,
  ...,
  reduction = "sum_over_batch_size",
  name = "mean_squared_error"
)

Arguments

`y_true`	Ground truth values 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"` or `NULL`.
`name`	Optional name for the loss instance.

Value

Mean squared error values with shape = ⁠[batch_size, d0, .. dN-1]⁠.

Examples

y_true <- random_uniform(c(2, 3), 0, 2)
y_pred <- random_uniform(c(2, 3))
loss <- loss_mean_squared_error(y_true, y_pred)

Other losses:
Loss()
loss_binary_crossentropy()
loss_binary_focal_crossentropy()
loss_categorical_crossentropy()
loss_categorical_focal_crossentropy()
loss_categorical_hinge()
loss_cosine_similarity()
loss_dice()
loss_hinge()
loss_huber()
loss_kl_divergence()
loss_log_cosh()
loss_mean_absolute_error()
loss_mean_absolute_percentage_error()
loss_mean_squared_logarithmic_error()
loss_poisson()
loss_sparse_categorical_crossentropy()
loss_squared_hinge()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_hinge()
metric_huber()
metric_kl_divergence()
metric_log_cosh()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_poisson()
metric_sparse_categorical_crossentropy()
metric_squared_hinge()