Metraipolis › archive › dc_cce088134e2f
Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification — arXiv:2608.10007
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10007
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:50.233Z
- SHA-256 of the archived text
1567454fa796d5a32390100a91a6af709fdf4424b05e2f5350137608d9b7b3b7- Stable URL of this page
https://metraipolis.com/documento/dc_cce088134e2f
How to cite
Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification — arXiv:2608.10007 — arXiv (en), https://arxiv.org/abs/2608.10007 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cce088134e2f (Metraipolis archive dc_cce088134e2f, sha256 1567454fa796d5a32390100a91a6af709fdf4424b05e2f5350137608d9b7b3b7)
BibTeX
@misc{dccce088134e2f,
title = {Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification — arXiv:2608.10007},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10007},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cce088134e2f; sha256 1567454fa796d5a32390100a91a6af709fdf4424b05e2f5350137608d9b7b3b7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10007. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied to real-world datasets containing noise and outliers. Furthermore, the propagation of contaminated features across hidden layers negatively influences the decision-making capability of these models. To overcome these limitations, we propose intuitionistic fuzzy dRVFL (IF-dRVFL) and intuitionistic fuzzy edRVFL (IF-edRVFL) frameworks that enhance model robustness. The proposed models unify intuitionistic fuzzy theory to exploit sample neighborhood information in the kernel space by jointly considering membership and non-membership degrees for each sample. Membership degrees are computed based on the distance of samples from their respective class centroids, while non-membership degrees quantify sample heterogeneity within local neighborhoods. These measures are employed to assign adaptive weights to training samples, enabling effective discrimination among clean, noisy, and outlier data points. Extensive experiments conducted on UCI and KEEL benchmark datasets, with and without the presence of Gaussian noise, demonstrate the superiority of the proposed IF-dRVFL and IF-edRVFL models over existing SOTA fuzzy and non-fuzzy approaches. The source code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.10007 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:57:28.326Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).