initializer_truncated_normal: Initializer that generates a truncated normal distribution.

In keras: R Interface to 'Keras'

Initializer that generates a truncated normal distribution.

Description

These values are similar to values from an initializer_random_normal() except that values more than two standard deviations from the mean are discarded and re-drawn. This is the recommended initializer for neural network weights and filters.

Usage

initializer_truncated_normal(mean = 0, stddev = 0.05, seed = NULL)

Arguments

mean	Mean of the random values to generate.
stddev	Standard deviation of the random values to generate.
seed	Integer used to seed the random generator.

See Also

Other initializers: initializer_constant(), initializer_glorot_normal(), initializer_glorot_uniform(), initializer_he_normal(), initializer_he_uniform(), initializer_identity(), initializer_lecun_normal(), initializer_lecun_uniform(), initializer_ones(), initializer_orthogonal(), initializer_random_normal(), initializer_random_uniform(), initializer_variance_scaling(), initializer_zeros()

keras documentation built on May 29, 2024, 3:20 a.m.