• Home
  • Search
  • Efficient Ensemble Broad Learning System Based on Dropout and DropConnect
  • Cite Icon1
  • https://doi.org/10.62678/ijics202403.10110Copy DOI Icon

Efficient Ensemble Broad Learning System Based on Dropout and DropConnect

  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Broad Learning System is an emerged efficient algorithm for training single hidden layer feedforward neural network (SLFN) with fast speed and good generalization ability. However, it is very difficult to determine the appropriate broad learning system structure and broad learning system may perform overfitting due to the dependence between nodes in processing fully connected network. In order to deal with these problems, efficient ensemble broad learning system based on Dropout and DropConnect are proposed in this paper. The proposed Dropout Ensemble Broad Learning System randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction stability. The DropConnect Ensemble Broad Learning System randomly drops connect weights to generate more complementary models by adding input attribute disturbance. The experimental results and statistical analysis on UCI data sets confirm that the proposed method can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning system and also show that the proposed approaches outperform the original BLS on prediction stability and classification accuracy.

Similar Papers
  • Research Article
  • Citations42

Ensemble dropout extreme learning machine via fuzzy integral for data classification

  • Sep 22, 2017
  • Neurocomputing
  • Junhai Zhai +2
  • PDF
  • Research Article
  • Citations5

An Ensemble Broad Learning System (BLS) for Evaluating Landslide Susceptibility in Taiyuan City, Northern China

  • Jul 20, 2023
  • Applied Sciences
  • Dekang Zhao +7
  • Conference Article
  • Citations17

State Preserving Extreme Learning Machine for face recognition

  • Jul 01, 2015
  • Md Zahangir Alom +3
  • Book Chapter
  • Citations4

A Fast Incremental Method Based on Regularized Extreme Learning Machine

  • Jan 01, 2015
  • Zhixin Xu +1
  • Conference Article
  • Citations16

Evolutionary algorithm for training compact single hidden layer feedforward neural networks

  • Jun 01, 2008
  • Hieu Trung Huynh +1
  • Research Article
  • Citations13

From WASD to BLS with application to pattern classification

  • Apr 30, 2021
  • Applied Soft Computing
  • Mei Liu +4
  • Conference Article
  • Citations9

ELM based LF temperature prediction model and its online sequential learning

  • May 01, 2012
  • Wu Lv +2
  • PDF
  • Research Article
  • Citations60

Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine

  • Jan 10, 2018
  • Sensors (Basel, Switzerland)
  • Feixiang Zhao +4
  • Research Article
  • Citations46

Incremental regularized extreme learning machine and it׳s enhancement

  • Aug 12, 2015
  • Neurocomputing
  • Zhixin Xu +3
  • Research Article
  • Citations82

A systematic design of interval type-2 fuzzy logic system using extreme learning machine for electricity load demand forecasting

  • Mar 16, 2016
  • International Journal of Electrical Power & Energy Systems
  • Saima Hassan +3
  • Book Chapter

Orthogonal Basis Extreme Learning Algorithm and Function Approximation

  • Jan 01, 2015
  • Ying Li +2
  • Conference Article
  • Citations5

ELM weighted hybrid modeling and its online modification

  • May 01, 2016
  • Shao-Ming Yang +4
  • Research Article
  • Citations125

On the approximation by single hidden layer feedforward neural networks with fixed weights

  • Dec 18, 2017
  • Neural Networks
  • Namig J Guliyev +1
  • Research Article
  • Citations57

Constitutive models of magnetorheological fluids having temperature-dependent prediction parameter

  • Jul 31, 2018
  • Smart Materials and Structures
  • I Bahiuddin +5
  • Book Chapter

A Heterogeneous AdaBoost Ensemble Based Extreme Learning Machines for Imbalanced Data

  • May 13, 2022
  • Adnan Omer Abuassba +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.