layer_gaussian_noise: Apply additive zero-centered Gaussian noise.

View source: R/layers-noise.R

layer_gaussian_noiseR Documentation

Apply additive zero-centered Gaussian noise.

Description

This is useful to mitigate overfitting (you could see it as a form of random data augmentation). Gaussian Noise (GS) is a natural choice as corruption process for real valued inputs. As it is a regularization layer, it is only active at training time.

Usage

layer_gaussian_noise(object, stddev, seed = NULL, ...)

Arguments

object

What to compose the new Layer instance with. Typically a Sequential model or a Tensor (e.g., as returned by layer_input()). The return value depends on object. If object is:

  • missing or NULL, the Layer instance is returned.

  • a Sequential model, the model with an additional layer is returned.

  • a Tensor, the output tensor from layer_instance(object) is returned.

stddev

float, standard deviation of the noise distribution.

seed

Integer, optional random seed to enable deterministic behavior.

...

standard layer arguments.

Input shape

Arbitrary. Use the keyword argument input_shape (list of integers, does not include the samples axis) when using this layer as the first layer in a model.

Output shape

Same shape as input.

See Also

Other noise layers: layer_alpha_dropout(), layer_gaussian_dropout()


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