← Back to all news
arXiv Machine Learning

IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss

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.

Related stories

Hugging Face Trending Papers
Sep 2

IFW-BLS: Dual-Robust Broad Learning System with Intuitionistic Fuzzy Wave Loss

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.

benchmarks
More like this →
arXiv Machine Learning
Sep 1

Robust Broad Learning System with Wave Loss for Classification under Data Uncertainty

The paper introduces Wave-BLS, a robust Broad Learning System that replaces the traditional squared error loss with an asymmetric, bounded, and smooth wave loss function. This change allows controlled penalization of large errors and eliminates the need for matrix inversion by using a Nesterov accelerated gradient scheme. Experiments on 30 UCI datasets show that Wave-BLS consistently outperforms classical BLS and other robust variants, with statistical tests confirming the significance of the improvements and demonstrating greater resilience to noise and outliers.

By Mushir Akhtar, A. Varshney, A. Quadir, A. Rahaman, M. Tanveer, Mohd. Arshad
benchmarks
More like this →
arXiv AI
Aug 12

Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification

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.

By M. Sajid, A. Quadir, A. Rahaman, P. N. Suganthan, M. Tanveer
benchmarks
More like this →
arXiv Computer Vision
Sep 15

Sparsity-Adaptive Sharpness-Aware Minimization

The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.

By Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato
efficiency
More like this →