• Home
  • Search
  • Advancing broad learning through structured feature generation
  • Cite Icon1
  • https://doi.org/10.1016/j.eswa.2025.129948Copy DOI Icon

Advancing broad learning through structured feature generation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

• Tackles randomness redundancy in broad learning systems with structured design. • Improves accuracy compared to classic broad learning systems in classification and regression tasks. • Addresses the lack of robustness in random neural architectures when faced with noise and scarce data. • Structured network design produces interpretable feature maps, enabling transparent AI decisions. Deep neural networks achieve strong performance in big data scenarios, while requiring extensive iterative parameter optimization, making them inefficient and suboptimal in scarce data scenarios. Broad Learning System (BLS) has gained popularity as an efficient, effective, and incremental learning model. BLS relies on independent and identically distributed random feature generation. Although efficient, the literature has shown that this approach can lead to suboptimal and redundant representations. This paper introduces Structured BLS (SBLS), a novel reinterpretation of BLS components. SBLS enhances latent features by incorporating a structured random basis, which provides a beneficial inductive bias that promotes neuronal specialization to learn specific patterns in the data while reducing the redundancy issue of the classic BLS. Experimental results in various classification and regression datasets demonstrate that SBLS outperforms BLS in terms of performance, robustness to noise, and interpretability, while remaining efficient and easy to deploy. Our findings emphasize the need for focused feature generation through random weights in neural networks and reservoir computing. In fact, we are transitioning from a chaotic to a controlled exploration of patterns. Moreover, we illustrate how our approach can incorporate task-specific knowledge into neuron behavior by design. SBLS has practical implications for real-world applications that involve data scarcity. By refining the way randomness is exploited in neural networks, our work challenges the conventional wisdom that improved performance requires deeper architectures or complex optimization strategies. Instead, we show that intelligent feature generation can unlock significant gains at minimal additional cost. 1

Similar Papers
  • Research Article
  • Citations4

Broad Multitask Learning System With Group Sparse Regularization.

  • May 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Jintao Huang +3
  • Research Article
  • Citations9

Broad Minimax Probability Learning System and its Application in Regression Modeling

  • Mar 01, 2023
  • IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • Fei Chu +4
  • PDF
  • Research Article
  • Citations8

Network Intrusion Detection Based on Deep Belief Network Broad Equalization Learning System

  • Jul 31, 2024
  • Electronics
  • Miaolei Deng +5
  • Research Article
  • Citations2

Discriminative projective dictionary pair based broad metric learning system: algorithm and its applications in pattern classification

  • Jul 19, 2025
  • Artificial Intelligence Review
  • Junwei Duan +1
  • Research Article
  • Citations18

A Broad Ensemble Learning System for Drifting Stream Classification

  • Jan 01, 2023
  • IEEE Access
  • Sepehr Bakhshi +3
  • Research Article
  • Citations13

From WASD to BLS with application to pattern classification

  • Apr 30, 2021
  • Applied Soft Computing
  • Mei Liu +4
  • Research Article
  • Citations62

Multi-Attn BLS: Multi-head attention mechanism with broad learning system for chaotic time series prediction

  • Nov 21, 2022
  • Applied Soft Computing
  • Liyun Su +2
  • Research Article
  • Citations31

A Hybrid Recursive Implementation of Broad Learning With Incremental Features.

  • Dec 22, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Di Liu +3
  • Research Article
  • Citations20

Extreme Fuzzy Broad Learning System: Algorithm, Frequency Principle, and Applications in Classification and Regression.

  • Feb 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Junwei Duan +6
  • Book Chapter
  • Citations1

A Broad Learning System Based on the Idea of Vertical Federated Learning

  • Jan 01, 2023
  • Junrong Ge +3
  • Conference Article
  • Citations118

EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks and Broad Learning System

  • Dec 01, 2018
  • Xue-Han Wang +5
  • Research Article
  • Citations8

A novel simultaneous monitoring method for surface roughness and tool wear in milling process

  • Mar 08, 2025
  • Scientific Reports
  • Ruilin Liu +1
  • Conference Article
  • Citations7

On the Construction of Hierarchical Broad Learning Neural Network: An Alternative Way of Deep Learning

  • Nov 01, 2018
  • Vikas Chauhan +1
  • Research Article
  • Citations21

Modal-Regression-Based Broad Learning System for Robust Regression and Classification.

  • Sep 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Licheng Liu +3
  • Conference Article

A Fast Method of Function Approximation using Broad Learning System

  • Sep 01, 2019
  • Yuzhuo Ma +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.