autoencoder_denoising: Create a denoising autoencoder

View source: R/autoencoder_denoising.R

autoencoder_denoisingR Documentation

Create a denoising autoencoder

Description

A denoising autoencoder trains with noisy data in order to create a model able to reduce noise in reconstructions from input data

Usage

autoencoder_denoising(
  network,
  loss = "mean_squared_error",
  noise_type = "zeros",
  ...
)

Arguments

network

Layer construct of class "ruta_network"

loss

Loss function to be optimized

noise_type

Type of data corruption which will be used to train the autoencoder, as a character string. Available types:

  • "zeros" Randomly set components to zero (⁠\link{noise_zeros}⁠)

  • "ones" Randomly set components to one (⁠\link{noise_ones}⁠)

  • "saltpepper" Randomly set components to zero or one (⁠\link{noise_saltpepper}⁠)

  • "gaussian" Randomly offset each component of an input as drawn from Gaussian distributions with the same variance (additive Gaussian noise, ⁠\link{noise_gaussian}⁠)

  • "cauchy" Randomly offset each component of an input as drawn from Cauchy distributions with the same scale (additive Cauchy noise, ⁠\link{noise_cauchy}⁠)

...

Extra parameters to customize the noisy filter:

  • p The probability that each instance in the input data which will be altered by random noise (for "zeros", "ones" and "saltpepper")

  • var or sd The variance or standard deviation of the Gaussian distribution from which additive noise will be drawn (for "gaussian", only one of those parameters is necessary)

  • scale For the Cauchy distribution

Value

A construct of class "ruta_autoencoder"

References

See Also

Other autoencoder variants: autoencoder_contractive(), autoencoder_robust(), autoencoder_sparse(), autoencoder_variational(), autoencoder()


fdavidcl/ruta documentation built on July 5, 2023, 6:32 p.m.