Harmony Search Algorithms for Optimizing Extreme Learning Machines

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

doi:10.1007/978-981-15-8603-3_2

Harmony Search Algorithms for Optimizing Extreme Learning Machines

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

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 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 language	English
Title of host publication	Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020
Editors	Sinan Melih Nigdeli, Gebrail Bekdas, Joong Hoon Kim, Anupam Yadav
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	11-20
Number of pages	10
ISBN (Print)	9789811586026
DOIs	https://doi.org/10.1007/978-981-15-8603-3_2
Publication status	Published - 2021
Event	6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020 - Istanbul, Turkey Duration: 2020 Apr 22 → 2020 Apr 24

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1275
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020
Country/Territory	Turkey
City	Istanbul
Period	20/4/22 → 20/4/24

Bibliographical note

Funding Information:
Acknowledgements This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2019R1A2B5B03069810).

Publisher Copyright:
© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Classification
Extreme Learning Machine
Harmony Search

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-981-15-8603-3_2

Cite this

Al-Shamiri, A. K., Sadollah, A., & Kim, J. H. (2021). Harmony Search Algorithms for Optimizing Extreme Learning Machines. In S. M. Nigdeli, G. Bekdas, J. H. Kim, & A. Yadav (Eds.), Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020 (pp. 11-20). (Advances in Intelligent Systems and Computing; Vol. 1275). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-8603-3_2

Harmony Search Algorithms for Optimizing Extreme Learning Machines. / Al-Shamiri, Abobakr Khalil; Sadollah, Ali; Kim, Joong Hoon.
Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020. ed. / Sinan Melih Nigdeli; Gebrail Bekdas; Joong Hoon Kim; Anupam Yadav. Springer Science and Business Media Deutschland GmbH, 2021. p. 11-20 (Advances in Intelligent Systems and Computing; Vol. 1275).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Al-Shamiri, AK, Sadollah, A & Kim, JH 2021, Harmony Search Algorithms for Optimizing Extreme Learning Machines. in SM Nigdeli, G Bekdas, JH Kim & A Yadav (eds), Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020. Advances in Intelligent Systems and Computing, vol. 1275, Springer Science and Business Media Deutschland GmbH, pp. 11-20, 6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020, Istanbul, Turkey, 20/4/22. https://doi.org/10.1007/978-981-15-8603-3_2

Al-Shamiri AK, Sadollah A, Kim JH. Harmony Search Algorithms for Optimizing Extreme Learning Machines. In Nigdeli SM, Bekdas G, Kim JH, Yadav A, editors, Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 11-20. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-981-15-8603-3_2

Al-Shamiri, Abobakr Khalil ; Sadollah, Ali ; Kim, Joong Hoon. / Harmony Search Algorithms for Optimizing Extreme Learning Machines. Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020. editor / Sinan Melih Nigdeli ; Gebrail Bekdas ; Joong Hoon Kim ; Anupam Yadav. Springer Science and Business Media Deutschland GmbH, 2021. pp. 11-20 (Advances in Intelligent Systems and Computing).

@inproceedings{75a3be6a5f4f473597ef8edc6c07d03b,

title = "Harmony Search Algorithms for Optimizing Extreme Learning Machines",

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.",

keywords = "Classification, Extreme Learning Machine, Harmony Search",

author = "Al-Shamiri, \{Abobakr Khalil\} and Ali Sadollah and Kim, \{Joong Hoon\}",

note = "Funding Information: Acknowledgements This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2019R1A2B5B03069810). Publisher Copyright: {\textcopyright} 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020 ; Conference date: 22-04-2020 Through 24-04-2020",

year = "2021",

doi = "10.1007/978-981-15-8603-3\_2",

language = "English",

isbn = "9789811586026",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "11--20",

editor = "Nigdeli, \{Sinan Melih\} and Gebrail Bekdas and Kim, \{Joong Hoon\} and Anupam Yadav",

booktitle = "Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020",

address = "Germany",

}

TY - GEN

T1 - Harmony Search Algorithms for Optimizing Extreme Learning Machines

AU - Al-Shamiri, Abobakr Khalil

AU - Sadollah, Ali

AU - Kim, Joong Hoon

N1 - Funding Information: Acknowledgements This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. 2019R1A2B5B03069810). Publisher Copyright: © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Classification

KW - Extreme Learning Machine

KW - Harmony Search

UR - https://www.scopus.com/pages/publications/85097102551

U2 - 10.1007/978-981-15-8603-3_2

DO - 10.1007/978-981-15-8603-3_2

M3 - Conference contribution

AN - SCOPUS:85097102551

SN - 9789811586026

T3 - Advances in Intelligent Systems and Computing

SP - 11

EP - 20

BT - Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications - ICHSA 2020

A2 - Nigdeli, Sinan Melih

A2 - Bekdas, Gebrail

A2 - Kim, Joong Hoon

A2 - Yadav, Anupam

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2020

Y2 - 22 April 2020 through 24 April 2020

ER -

Harmony Search Algorithms for Optimizing Extreme Learning Machines

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this