TSLSTMplus: Long-Short Term Memory for Time-Series Forecasting, Enhanced

The LSTM (Long Short-Term Memory) model is a Recurrent Neural Network (RNN) based architecture that is widely used for time series forecasting. Customizable configurations for the model are allowed, improving the capabilities and usability of this model compared to other packages. This package is based on 'keras' and 'tensorflow' modules and the algorithm of Paul and Garai (2021) <doi:10.1007/s00500-021-06087-4>.

Version: 1.0.4
Imports: keras, tensorflow, tsutils, stats, abind
Published: 2024-03-10
Author: Jaime Pizarroso Gonzalo [aut, ctb, cre], Antonio Muñoz San Roque [aut]
Maintainer: Jaime Pizarroso Gonzalo <jpizarroso at comillas.edu>
License: GPL-3
NeedsCompilation: no
In views: TimeSeries
CRAN checks: TSLSTMplus results

Documentation:

Reference manual: TSLSTMplus.pdf

Downloads:

Package source: TSLSTMplus_1.0.4.tar.gz
Windows binaries: r-devel: TSLSTMplus_1.0.4.zip, r-release: TSLSTMplus_1.0.4.zip, r-oldrel: TSLSTMplus_1.0.4.zip
macOS binaries: r-release (arm64): TSLSTMplus_1.0.4.tgz, r-oldrel (arm64): TSLSTMplus_1.0.4.tgz, r-release (x86_64): TSLSTMplus_1.0.4.tgz
Old sources: TSLSTMplus archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=TSLSTMplus to link to this page.