A Discrete Non-Additive Integral Based Interval-Valued Neural Network for Enhanced Prediction Reliability

Yassine Hmidy, Mouna Ben Mabrouk

2025

Abstract

In this paper, we propose to replace the perceptron of classical feedforward neural networks by a new aggregation function. In a recent paper, it has been shown that this new aggregation is a relevant learning model, simple to use, and informative as it outputs an interval whose size is correlated to the prediction error of the model. Unlike a classical neural network whose perceptron are usually composed of a linear aggregation and an activation function, the model we propose here is a mere composition of those aggregation functions. In order to show the relevance of using such a neural network, we rely on experiments comparing its performances with those of a classical neural network.

Paper Citation

in Harvard Style

Hmidy Y. and Ben Mabrouk M. (2025). A Discrete Non-Additive Integral Based Interval-Valued Neural Network for Enhanced Prediction Reliability. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 345-352. DOI: 10.5220/0013155900003890

in Bibtex Style

@conference{icaart25,
author={Yassine Hmidy and Mouna Ben Mabrouk},
title={A Discrete Non-Additive Integral Based Interval-Valued Neural Network for Enhanced Prediction Reliability},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={345-352},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013155900003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - A Discrete Non-Additive Integral Based Interval-Valued Neural Network for Enhanced Prediction Reliability
SN - 978-989-758-737-5
AU - Hmidy Y.
AU - Ben Mabrouk M.
PY - 2025
SP - 345
EP - 352
DO - 10.5220/0013155900003890
PB - SciTePress