arXiv:2608. 10007v1 Announce Type: cross Abstract: 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.
arXiv:2607. 05635v1 Announce Type: new Abstract: Random Vector Functional Link (RVFL) networks are popular due to their fast training and universal approximation capabilities.
arXiv:2607. 16728v1 Announce Type: new Abstract: The Broad Learning System (BLS) has been widely used for data classification and is based on a layer-by-layer feed-forward structure.
The paper introduces IFW-BLS, a Dual‑Robust Broad Learning System that enhances the traditional BLS by incorporating a bounded, asymmetric wave loss to protect against large residuals and by applying intuitionistic fuzzy scores to weight samples based on credibility. This dual approach mitigates the impact of noise, outliers, and ambiguous data points, while a Nesterov‑accelerated optimizer replaces the costly matrix inversion of conventional BLS. Experiments on UCI benchmarks and corruption tests demonstrate that IFW‑BLS outperforms baseline models and remains more stable under noisy conditions.
IFW-BLS is a Dual‑Robust Broad Learning System that enhances the standard Broad Learning System by incorporating two robustness mechanisms. It replaces the squared loss with a bounded, smooth, asymmetric wave loss to protect against large residuals, and applies intuitionistic fuzzy scores to weight samples based on global class consistency and local neighborhood conflict, thereby down‑weighting unreliable data. The model is optimized with a Nesterov accelerated gradient solver, avoiding explicit matrix inversion, and experiments on UCI benchmarks show it outperforms baseline models and remains stable under noise and outlier contamination.
RoBell-RVFL is a lightweight, quality‑aware generalized bell random vector functional link network designed to address class imbalance and noisy data in real‑world datasets. It uses a dual‑strategy sample‑level weighting: unit weights preserve minority class information, while a probability‑weighted generalized bell membership function suppresses noisy majority samples in a kernel‑induced feature space. Experiments on UCI and KEEL benchmarks, including tests with up to 40% label noise, show that RoBell‑RVFL consistently outperforms recent RVFL variants, demonstrating the importance of adaptive, quality‑aware sample weighting for robust learning.
arXiv:2609. 20194v1 Announce Type: cross Abstract: Triangular membership functions (MFs) are widely used in fuzzy systems because of their interpretability, low parameterization complexity, and strong locality properties.
The paper introduces GBFRVFL, a fuzzy granular-ball random vector functional link network designed to improve robustness in noisy, imbalanced, or uncertain data settings. It employs granular-ball computing to group raw samples into adaptive balls and proposes two membership assignment schemes: F-GBRVFL, which uses fuzzy membership to gauge ball reliability, and SDAP-GBRVFL, which introduces a statistical density‑adaptive Pythagorean membership that adjusts based on class variance, local sparsity, and ball compactness. Experiments on 37 UCI and KEEL datasets show that these models outperform baseline methods in both clean and noisy conditions, achieving higher accuracy and stability.
arXiv:2608. 05859v1 Announce Type: cross Abstract: Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably.
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
arXiv:2602. 00511v3 Announce Type: replace Abstract: We introduce \emph{Partition of Unity Neural Networks} (PUNNs), a neural-network architecture for multiclass classification based on the classical mathematical notion of a partition of unity.
arXiv:2608. 14773v1 Announce Type: cross Abstract: The efficient-KAN literature---covering Chebyshev, wavelet, and radial-basis-function variants of the original Kolmogorov-Arnold Network---has been benchmarked almost entirely on clean data.
arXiv:2510. 22021v3 Announce Type: replace Abstract: Safety-critical applications of machine learning require uncertainty estimates that support reliable worst-case analysis.