• Home
  • Search
  • Improving Generalization Capability of Extreme Learning Machine with Synthetic Instances Generation
  • Cite Icon1
  • https://doi.org/10.1007/978-3-319-70087-8_1Copy DOI Icon

Improving Generalization Capability of Extreme Learning Machine with Synthetic Instances Generation

  • Jan 1, 2017
  • Wei Ao +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, instead of modifying the framework of Extreme learning machine (ELM), we propose a learning algorithm to improve generalization ability of ELM with Synthetic Instances Generation (SIGELM). We focus on optimizing the output-layer weights via adding informative synthetic instances to the training dataset at each learning step. In order to get the required synthetic instances, a neighborhood is determined for each high-uncertainty training sample and then the synthetic instances which enhance the training performance of ELM are selected in the neighborhood. The experimental results based on 4 representative regression datasets of KEEL demonstrate that our proposed SIGELM obviously improves the generalization capability of ELM and effectively decreases the phenomenon of over-fitting.

Similar Papers
  • Research Article
  • Citations10

Enhancement of Extreme Learning Machine for Estimating Blocking Probability of OCS Networks With Fixed-Alternate Routing

  • Jan 01, 2019
  • IEEE Access
  • Shuo Li +3
  • Research Article
  • Citations123

An integrated framework of Extreme Learning Machines for predicting scour at pile groups in clear water condition

  • Jan 16, 2018
  • Coastal Engineering
  • Isa Ebtehaj +4
  • Research Article
  • Citations8

Musical pitch estimation using a supervised single hidden layer feed-forward neural network

  • Aug 01, 2012
  • Expert Systems with Applications
  • Pat Taweewat +1
  • Research Article
  • Citations171

Integrated framework of extreme learning machine (ELM) based on improved atom search optimization for short-term wind speed prediction

  • Dec 14, 2021
  • Energy Conversion and Management
  • Lei Hua +4
  • Research Article
  • Citations14

Joint Domain Matching and Classification for cross-domain adaptation via ELM

  • Jan 25, 2019
  • Neurocomputing
  • Chao Chen +3
  • Research Article
  • Citations61

AUC-Based Extreme Learning Machines for Supervised and Semi-Supervised Imbalanced Classification

  • Apr 10, 2020
  • IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • Guanjin Wang +2
  • Conference Article

A Great Learning Stratagem through Artificial Bee Colony Technique for Grouping

  • Apr 20, 2023
  • Shweta Singh +3
  • Research Article
  • Citations48

Experimental Study on Extreme Learning Machine Applications for Speech Enhancement

  • Jan 01, 2017
  • IEEE Access
  • Tassadaq Hussain +5
  • Research Article
  • Citations33

METAGENOMIC TAXONOMIC CLASSIFICATION USING EXTREME LEARNING MACHINES

  • Aug 01, 2012
  • Journal of Bioinformatics and Computational Biology
  • Zeehasham Rasheed +1
  • Research Article

Classification of peanut variety based on hyperspectral imaging and improved extreme learning machine

  • Jan 29, 2025
  • Czech Journal of Food Sciences
  • Mengke Wang +5
  • Conference Article
  • Citations4

Blind equalization of QAM signals via extreme learning machine

  • Mar 01, 2018
  • Rong Yang +5
  • Research Article
  • Citations2

A combined improved dung beetle optimization and extreme learning machine framework for precise SOC estimation

  • May 20, 2025
  • Scientific Reports
  • Kaihua Yao +6
  • Research Article
  • Citations6

Negative correlation learning in the extreme learning machine framework

  • Mar 02, 2020
  • Neural Computing and Applications
  • Carlos Perales-González +4
  • Research Article
  • Citations4

ELM-Based Imbalanced Data Classification-A Review

  • May 28, 2024
  • Informatica
  • Brajendra Singh Rajput +3
  • Research Article
  • Citations49

BC-QNet: A quantum-infused ELM model for breast cancer diagnosis

  • Apr 24, 2024
  • Computers in Biology and Medicine
  • Anas Bilal +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.