Create a denoising autoencoder

Source: R/autoencoder_denoising.R

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

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"