{"slug": "uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification", "title": "Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification", "summary": "Researchers propose intuitionistic fuzzy deep Random Vector Functional Link (IF-dRVFL) and ensemble deep RVFL (IF-edRVFL) frameworks that assign adaptive weights to training samples based on membership and non-membership degrees, improving robustness against noise and outliers. Experiments on UCI and KEEL benchmark datasets show the models outperform existing state-of-the-art fuzzy and non-fuzzy approaches. Source code is available at https://github.com/mtanveer1/IF-edRVFL.", "body_md": "arXiv:2608.10007v1 Announce Type: new\nAbstract: 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 https://github.com/mtanveer1/IF-edRVFL.", "url": "https://wpnews.pro/news/uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification", "canonical_source": "https://arxiv.org/abs/2608.10007", "published_at": "2026-08-12 04:00:00+00:00", "updated_at": "2026-08-12 04:12:49.301262+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks"], "entities": ["IF-dRVFL", "IF-edRVFL", "UCI", "KEEL", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification", "markdown": "https://wpnews.pro/news/uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification.md", "text": "https://wpnews.pro/news/uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification.txt", "jsonld": "https://wpnews.pro/news/uncertainty-aware-ensemble-deep-randomized-neural-networks-for-classification.jsonld"}}