Broad stochastic configuration residual learning system for norm-convergent universal approximation
Preprint
Abstract
Universal approximation serves as the foundation of neural network learning algorithms. However, some networks establish their universal approximation property by demonstrating that the iterative errors converge in probability measure rather than the more rigorous norm convergence, which makes the universal approximation property of randomized learning networks highly sensitive to random parameter selection, Broad residual learning system (BRLS), as a member of randomized learning models, also encounters this issue. We theoretically demonstrate the limitation of its universal approximation property, that is, the iterative errors do not satisfy norm convergence if the selection of random parameters is inappropriate and the convergence rate meets certain conditions. To address this issue, we propose the broad stochastic configuration residual learning system (BSCRLS) algorithm, which features a novel supervisory mechanism adaptively constraining the range settings of random parameters on the basis of BRLS framework, Furthermore, we prove the universal approximation theorem of BSCRLS based on the more stringent norm convergence. Three versions of incremental BSCRLS algorithms are presented to satisfy the application requirements of various network updates. Solar panels dust detection experiments are performed on publicly available dataset and compared with 13 deep and broad learning algorithms. Experimental results reveal the effectiveness and superiority of BSCRLS algorithms.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- A novel broad learning network with residual techniquePattern Recognition, 2025
- Deep metric learning in projected-hypersphere spacePattern Recognition, 2024
- Self-organizing hierarchical incremental learning framework and universal approximation analysis based on stochastic configuration mechanismInformation Sciences, 2024
- Deep network embedding with dimension selectionNeural Networks, 2024
- Self-balancing Incremental Broad Learning System with privacy protectionNeural Networks, 2024
- Stream label distribution learning processing via broad learning systemInformation Sciences, 2024
- EEG-based emotion recognition using MobileNet Recurrent Neural Network with time-frequency featuresApplied Soft Computing, 2024
- Iterative magnitude pruning-based light-version of AlexNet for skin cancer classificationNeural Computing and Applications, 2023
- Approximation with random bases: Pro et ContraInformation Sciences, 2016
- Neural-net computing and the intelligent control of systemsInternational Journal of Control, 1992