evreg: Evidential Regression

An implementation of the 'Evidential Neural Network for Regression' model recently introduced in Denoeux (2023) <doi:10.36227/techrxiv.21791831.v1>. In this model, prediction uncertainty is quantified by Gaussian random fuzzy numbers as introduced in Denoeux (2023) <doi:10.1016/j.fss.2022.06.004>. The package contains functions for training the network, tuning hyperparameters by cross-validation or the hold-out method, and making predictions. It also contains utilities for making calculations with Gaussian random fuzzy numbers (such as, e.g., computing the degrees of belief and plausibility of an interval, or combining Gaussian random fuzzy numbers).

Version: 1.0.1
Depends: R (≥ 3.1.0)
Imports: evclust, stats
Suggests: knitr, rmarkdown, nnet, MASS, ggplot2
Published: 2023-02-04
Author: Thierry Denoeux ORCID iD [aut, cre]
Maintainer: Thierry Denoeux <tdenoeux at utc.fr>
License: GPL-3
NeedsCompilation: no
Materials: NEWS
In views: MachineLearning
CRAN checks: evreg results


Reference manual: evreg.pdf
Vignettes: Introduction to the evreg package


Package source: evreg_1.0.1.tar.gz
Windows binaries: r-devel: evreg_1.0.1.zip, r-release: evreg_1.0.1.zip, r-oldrel: evreg_1.0.1.zip
macOS binaries: r-release (arm64): evreg_1.0.1.tgz, r-oldrel (arm64): evreg_1.0.1.tgz, r-release (x86_64): evreg_1.0.1.tgz, r-oldrel (x86_64): evreg_1.0.1.tgz
Old sources: evreg archive


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