Extreme learning machine

A review

Musatafa Abbas Abbood Albadr, Sabrina Tiun

Research output: Contribution to journalReview article

12 Citations (Scopus)

Abstract

Feedforward neural networks (FFNN) have been utilised for various research in machine learning and they have gained a significantly wide acceptance. However, it was recently noted that the feedforward neural network has been functioning slower than needed. As a result, it has created critical bottlenecks among its applications. Extreme Learning Machines (ELM) were suggested as alternative learning algorithms instead of FFNN. The former is characterised by single-hidden layer feedforward neural networks (SLFN). It selects hidden nodes randomly and analytically determines their output weight. This review aims to, first, present a short mathematical explanation to explain the basic ELM. Second, because of its notable simplicity, efficiency, and remarkable generalisation performance, ELM has had wide uses in various domains, such as computer vision, biomedical engineering, control and robotics, system identification, etc. Thus, in this review, we will aim to present a complete view of these ELM advances for different applications. Finally, ELM’s strengths and weakness will be presented, along with its future perspectives.

Original languageEnglish
Pages (from-to)4610-4623
Number of pages14
JournalInternational Journal of Applied Engineering Research
Volume12
Issue number14
Publication statusPublished - 1 Jan 2017

Fingerprint

Feedforward neural networks
Learning systems
Biomedical engineering
Learning algorithms
Computer vision
Identification (control systems)
Robotics

Keywords

  • Extreme learning machine
  • Single-hidden layer feedforward neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Extreme learning machine : A review. / Albadr, Musatafa Abbas Abbood; Tiun, Sabrina.

In: International Journal of Applied Engineering Research, Vol. 12, No. 14, 01.01.2017, p. 4610-4623.

Research output: Contribution to journalReview article

Albadr, Musatafa Abbas Abbood ; Tiun, Sabrina. / Extreme learning machine : A review. In: International Journal of Applied Engineering Research. 2017 ; Vol. 12, No. 14. pp. 4610-4623.
@article{cadecaa6d9eb42db829657c26d118c14,
title = "Extreme learning machine: A review",
abstract = "Feedforward neural networks (FFNN) have been utilised for various research in machine learning and they have gained a significantly wide acceptance. However, it was recently noted that the feedforward neural network has been functioning slower than needed. As a result, it has created critical bottlenecks among its applications. Extreme Learning Machines (ELM) were suggested as alternative learning algorithms instead of FFNN. The former is characterised by single-hidden layer feedforward neural networks (SLFN). It selects hidden nodes randomly and analytically determines their output weight. This review aims to, first, present a short mathematical explanation to explain the basic ELM. Second, because of its notable simplicity, efficiency, and remarkable generalisation performance, ELM has had wide uses in various domains, such as computer vision, biomedical engineering, control and robotics, system identification, etc. Thus, in this review, we will aim to present a complete view of these ELM advances for different applications. Finally, ELM’s strengths and weakness will be presented, along with its future perspectives.",
keywords = "Extreme learning machine, Single-hidden layer feedforward neural networks",
author = "Albadr, {Musatafa Abbas Abbood} and Sabrina Tiun",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "12",
pages = "4610--4623",
journal = "International Journal of Applied Engineering Research",
issn = "0973-4562",
publisher = "Research India Publications",
number = "14",

}

TY - JOUR

T1 - Extreme learning machine

T2 - A review

AU - Albadr, Musatafa Abbas Abbood

AU - Tiun, Sabrina

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Feedforward neural networks (FFNN) have been utilised for various research in machine learning and they have gained a significantly wide acceptance. However, it was recently noted that the feedforward neural network has been functioning slower than needed. As a result, it has created critical bottlenecks among its applications. Extreme Learning Machines (ELM) were suggested as alternative learning algorithms instead of FFNN. The former is characterised by single-hidden layer feedforward neural networks (SLFN). It selects hidden nodes randomly and analytically determines their output weight. This review aims to, first, present a short mathematical explanation to explain the basic ELM. Second, because of its notable simplicity, efficiency, and remarkable generalisation performance, ELM has had wide uses in various domains, such as computer vision, biomedical engineering, control and robotics, system identification, etc. Thus, in this review, we will aim to present a complete view of these ELM advances for different applications. Finally, ELM’s strengths and weakness will be presented, along with its future perspectives.

AB - Feedforward neural networks (FFNN) have been utilised for various research in machine learning and they have gained a significantly wide acceptance. However, it was recently noted that the feedforward neural network has been functioning slower than needed. As a result, it has created critical bottlenecks among its applications. Extreme Learning Machines (ELM) were suggested as alternative learning algorithms instead of FFNN. The former is characterised by single-hidden layer feedforward neural networks (SLFN). It selects hidden nodes randomly and analytically determines their output weight. This review aims to, first, present a short mathematical explanation to explain the basic ELM. Second, because of its notable simplicity, efficiency, and remarkable generalisation performance, ELM has had wide uses in various domains, such as computer vision, biomedical engineering, control and robotics, system identification, etc. Thus, in this review, we will aim to present a complete view of these ELM advances for different applications. Finally, ELM’s strengths and weakness will be presented, along with its future perspectives.

KW - Extreme learning machine

KW - Single-hidden layer feedforward neural networks

UR - http://www.scopus.com/inward/record.url?scp=85036636288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85036636288&partnerID=8YFLogxK

M3 - Review article

VL - 12

SP - 4610

EP - 4623

JO - International Journal of Applied Engineering Research

JF - International Journal of Applied Engineering Research

SN - 0973-4562

IS - 14

ER -