evreg

CRANevregMaRDI QIDQ65164FDOQ65164

Evidential Regression

T. Denœux

Last update: 9 November 2023

Copyright license: GNU General Public License, version 3.0

Software version identifier: 1.0.2, 1.0.0, 1.0.1, 1.0.3

Description

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).

Cites work

• Quantifying Prediction Uncertainty in Regression using Random Fuzzy Sets: the ENNreg model
• Reasoning with fuzzy and uncertain evidence using epistemic random fuzzy sets: General framework and practical models

This page was built for software: evreg