Harmony Search Algorithms for Optimizing Extreme Learning Machines

Abobakr Khalil Al-Shamiri, Ali Sadollah, Joong Hoon Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Extreme learning machine (ELM) is a non-iterative algorithm for training single-hidden layer feedforward neural network (SLFN). ELM has been shown to have good generalization performance and faster learning speed than conventional gradient-based learning algorithms. However, due to the random determination of the hidden neuron parameters (i.e., input weights and biases) ELM may require a large number of neurons in the hidden layer. In this paper, the original harmony search (HS) and its variants, namely, improved harmony search (IHS), global-best harmony search (GHS), and intelligent tuned harmony search (ITHS) are used to optimize the input weights and hidden biases of ELM. The output weights are analytically determined using the Moore–Penrose (MP) generalized inverse. The performance of the hybrid approaches is tested on several benchmark classification problems. The simulation results show that the integration of HS algorithms with ELM has obtained compact network architectures with good generalization performance.

Original languageEnglish
Title of host publicationProceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020
EditorsSinan Melih Nigdeli, Gebrail Bekdas, Joong Hoon Kim, Anupam Yadav
PublisherSpringer Science and Business Media Deutschland GmbH
Pages11-20
Number of pages10
ISBN (Print)9789811586026
DOIs
Publication statusPublished - 2021
Event6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020 - Istanbul, Turkey
Duration: 2020 Apr 222020 Apr 24

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1275
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020
Country/TerritoryTurkey
CityIstanbul
Period20/4/2220/4/24

Keywords

  • Classification
  • Extreme Learning Machine
  • Harmony Search

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Harmony Search Algorithms for Optimizing Extreme Learning Machines'. Together they form a unique fingerprint.

Cite this