DeepLSTMAutoencoder: DeepLSTMAutoencoder

In jdestefani/ExtendedDFML: Extended Dynamic Factor Machine Learner

Description

Auxiliary function defining a LSTM autoencoder model with two hidden layers

Usage

DeepLSTMAutoencoder(X, latent_dim = c(10, 5), time_window = 5)

Arguments

X	nxN matrix containing the N time series as columns, each one of length n time steps
latent_dim	Number of LSTM cells in the hidden layers - numeric vector
time_window	Size of time window (in time steps) for embedding - numeric scalar

Value

List containing:

• autoencoder: Fitted autoencoder model (full model) - Keras object

• encoder: Encoder part of the autoencoder model (Original space -> Latent Dimensions) - Keras object

• decoder: Decoder part of the autoencoder model (Latent Dimensions -> Original space) - Keras object

jdestefani/ExtendedDFML documentation built on Dec. 20, 2021, 10:04 p.m.