daltoolboxdp (version 1.2.737)

autoenc_stacked_e: Stacked Autoencoder - Encode

Description

Creates a deep learning stacked autoencoder to encode sequences of observations. The autoencoder layers are based on DAL Toolbox vanilla autoencoder and wrap a PyTorch implementation.

Usage

autoenc_stacked_e(
  input_size,
  encoding_size,
  batch_size = 32,
  num_epochs = 1000,
  learning_rate = 0.001,
  k = 3
)

Value

A autoenc_stacked_e object.

Arguments

input_size

input size

encoding_size

encoding size

batch_size

size for batch learning

num_epochs

number of epochs for training

learning_rate

learning rate

k

Integer. Number of autoencoder layers in the stack.

References

Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P.-A. (2010). Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion.

Examples

if (FALSE) {
X <- matrix(rnorm(1000), nrow = 50, ncol = 20)
ae <- autoenc_stacked_e(input_size = 20, encoding_size = 5, k = 3, num_epochs = 50)
ae <- daltoolbox::fit(ae, X)
Z  <- daltoolbox::transform(ae, X)
}

# See:
# https://github.com/cefet-rj-dal/daltoolbox/blob/main/autoencoder/autoenc_stacked_e.md