• Home
  • Search
  • Frequency Principle in Broad Learning System.
  • Cite Icon25
  • https://doi.org/10.1109/tnnls.2021.3081568Copy DOI Icon

Frequency Principle in Broad Learning System.

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

Deep neural networks have achieved breakthrough improvement in various application fields. Nevertheless, they usually suffer from a time-consuming training process because of the complicated structures of neural networks with a huge number of parameters. As an alternative, a fast and efficient discriminative broad learning system (BLS) is proposed, which takes the advantages of flat structure and incremental learning. The BLS has achieved outstanding performance in classification and regression problems. However, the previous studies ignored the reason why the BLS can generalize well. In this article, we focus on the interpretation from the viewpoint of the frequency domain. We discover the existence of the frequency principle in BLS, i.e., the BLS preferentially captures low-frequency components quickly and then fits the high frequencies during the incremental process of adding feature nodes and enhancement nodes. The frequency principle may be of great inspiration for expanding the application of BLS.

Similar Papers
  • Research Article
  • Citations106

Analysis and Variants of Broad Learning System

  • Jun 02, 2020
  • IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • Liang Zhang +9
  • 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
  • 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
  • Conference Article
  • Citations8

Broad Learning System and its Structural Variations

  • Sep 01, 2018
  • C L Philip Chen
  • Research Article
  • Citations551

Universal Approximation Capability of Broad Learning System and Its Structural Variations.

  • Sep 10, 2018
  • IEEE Transactions on Neural Networks and Learning Systems
  • C L Philip Chen +2
  • Research Article
  • Citations21

Broad learning approach to Surrogate-Assisted Multi-Objective evolutionary fuzzy clustering algorithm based on reference points for color image segmentation

  • Apr 01, 2022
  • Expert Systems with Applications
  • Feng Zhao +3
  • Conference Article
  • Citations6

Dense Broad Learning System based on Conjugate Gradient

  • Jul 01, 2020
  • Weidong Zou +2
  • Research Article
  • Citations13

From WASD to BLS with application to pattern classification

  • Apr 30, 2021
  • Applied Soft Computing
  • Mei Liu +4
  • Research Article
  • Citations1

Two-Dimensional Broad Learning System for Data Analytic

  • Dec 01, 2021
  • IEEE Transactions on Artificial Intelligence
  • Wei Dai +4
  • Research Article
  • Citations23

Incremental Bayesian broad learning system and its industrial application

  • Nov 13, 2020
  • Artificial Intelligence Review
  • Ying Liu +5
  • PDF
  • Research Article
  • Citations16

Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting

  • Apr 09, 2020
  • Complex & Intelligent Systems
  • Runshan Xie +1
  • Research Article
  • Citations10

Self-balancing Incremental Broad Learning System with privacy protection

  • Jun 06, 2024
  • Neural Networks
  • Weiwen Zhang +5
  • Research Article
  • Citations1

Advancing broad learning through structured feature generation

  • Mar 01, 2026
  • Expert Systems with Applications
  • Mario Mallea +2
  • Research Article
  • Citations7

Stacking multi-view broad learning system with residual structures for classification

  • Apr 05, 2024
  • Information Sciences
  • Tao Huang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.