daltoolboxdp (version 1.2.737)

autoenc_variational_ed: Variational Autoencoder - Encode-Decode

Description

Creates a deep learning variational autoencoder (VAE) that encodes and decodes sequences of observations. Wraps a PyTorch implementation.

Usage

autoenc_variational_ed(
  input_size,
  encoding_size,
  batch_size = 32,
  num_epochs = 1000,
  learning_rate = 0.001
)

Value

A autoenc_variational_ed 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

References

Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes.

Examples

if (FALSE) {
# Requirements: Python with torch installed and reticulate configured.

# 1) Sample data
X <- matrix(rnorm(1000), nrow = 50, ncol = 20)

# 2) Fit VAE encode-decode
ae <- autoenc_variational_ed(input_size = 20, encoding_size = 5, num_epochs = 50)
ae <- daltoolbox::fit(ae, X)

# 3) Reconstruct inputs
X_hat <- daltoolbox::transform(ae, X)
mean((X - X_hat)^2)
}

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