Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks

Artificial Neural Networks (ANNs) have demonstrated applicability and effectiveness in several domains, including classification tasks. Researchers have emphasized the training techniques of ANNs to identify appropriate weights and biases. However, conventional training techniques such as Gradient D...

Full description

Bibliographic Details
Main Authors: Al-Asaady, Maher Talal, Mohd Aris, Teh Noranis, Mohd Sharef, Nurfadhlina, Hamdan, Hazlina
Format: Article
Language:English
Published: Politeknik Negeri Padang 2025
Online Access:http://psasir.upm.edu.my/id/eprint/118626/
http://psasir.upm.edu.my/id/eprint/118626/1/118626.pdf
_version_ 1848867557859131392
author Al-Asaady, Maher Talal
Mohd Aris, Teh Noranis
Mohd Sharef, Nurfadhlina
Hamdan, Hazlina
author_facet Al-Asaady, Maher Talal
Mohd Aris, Teh Noranis
Mohd Sharef, Nurfadhlina
Hamdan, Hazlina
author_sort Al-Asaady, Maher Talal
building UPM Institutional Repository
collection Online Access
description Artificial Neural Networks (ANNs) have demonstrated applicability and effectiveness in several domains, including classification tasks. Researchers have emphasized the training techniques of ANNs to identify appropriate weights and biases. However, conventional training techniques such as Gradient Descent (GD) and Backpropagation (BP) often suffer from early convergence, dependence on initial parameters, and susceptibility to local optima, limiting their efficiency in complex, high-dimensional problems. Meta-heuristic algorithms (MHAs) offer a promising alternative as practical approaches for training ANNs, providing global search capabilities, robustness, and improved computational efficiency. Despite the growing use of MHAs, existing studies often focus on specific subsets of algorithms or narrow application domains, leaving a gap in understanding their comprehensive potential and comparative performance across diverse classification tasks. This paper addresses this gap by presenting a systematic review of advancements in training Multilayer Perceptron (MLP) neural networks using MHAs, analyzing 53 publications from 2014 to 2024. The research papers were chosen explicitly from four widely used databases: ScienceDirect, Scopus, Springer, and IEEE Xplore. Key contributions include a comparative analysis of evolutionary, swarm intelligence, physics-based, human-inspired algorithms, and hybrid approaches benchmarked on classification datasets. The study also highlights bibliometric trends, identifies underexplored areas such as adaptive and hybrid algorithms, and emphasizes the practical application of MHAs in optimizing ANN performance. This work is a significant resource for researchers, facilitating the identification of effective optimization methodologies and bridging the gap between theoretical advancements and real-world applications.
first_indexed 2025-11-15T14:38:24Z
format Article
id upm-118626
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:38:24Z
publishDate 2025
publisher Politeknik Negeri Padang
recordtype eprints
repository_type Digital Repository
spelling upm-1186262025-07-21T00:17:51Z http://psasir.upm.edu.my/id/eprint/118626/ Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks Al-Asaady, Maher Talal Mohd Aris, Teh Noranis Mohd Sharef, Nurfadhlina Hamdan, Hazlina Artificial Neural Networks (ANNs) have demonstrated applicability and effectiveness in several domains, including classification tasks. Researchers have emphasized the training techniques of ANNs to identify appropriate weights and biases. However, conventional training techniques such as Gradient Descent (GD) and Backpropagation (BP) often suffer from early convergence, dependence on initial parameters, and susceptibility to local optima, limiting their efficiency in complex, high-dimensional problems. Meta-heuristic algorithms (MHAs) offer a promising alternative as practical approaches for training ANNs, providing global search capabilities, robustness, and improved computational efficiency. Despite the growing use of MHAs, existing studies often focus on specific subsets of algorithms or narrow application domains, leaving a gap in understanding their comprehensive potential and comparative performance across diverse classification tasks. This paper addresses this gap by presenting a systematic review of advancements in training Multilayer Perceptron (MLP) neural networks using MHAs, analyzing 53 publications from 2014 to 2024. The research papers were chosen explicitly from four widely used databases: ScienceDirect, Scopus, Springer, and IEEE Xplore. Key contributions include a comparative analysis of evolutionary, swarm intelligence, physics-based, human-inspired algorithms, and hybrid approaches benchmarked on classification datasets. The study also highlights bibliometric trends, identifies underexplored areas such as adaptive and hybrid algorithms, and emphasizes the practical application of MHAs in optimizing ANN performance. This work is a significant resource for researchers, facilitating the identification of effective optimization methodologies and bridging the gap between theoretical advancements and real-world applications. Politeknik Negeri Padang 2025 Article PeerReviewed text en cc_by_sa_4 http://psasir.upm.edu.my/id/eprint/118626/1/118626.pdf Al-Asaady, Maher Talal and Mohd Aris, Teh Noranis and Mohd Sharef, Nurfadhlina and Hamdan, Hazlina (2025) Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks. International Journal on Informatics Visualization, 9 (2). pp. 658-673. ISSN 2549-9610; eISSN: 2549-9904 http://joiv.org/index.php/joiv/article/view/3109 10.62527/joiv.9.2.3109
spellingShingle Al-Asaady, Maher Talal
Mohd Aris, Teh Noranis
Mohd Sharef, Nurfadhlina
Hamdan, Hazlina
Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title_full Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title_fullStr Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title_full_unstemmed Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title_short Recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
title_sort recent advances in meta-heuristic algorithms for training multilayer perceptron neural networks
url http://psasir.upm.edu.my/id/eprint/118626/
http://psasir.upm.edu.my/id/eprint/118626/
http://psasir.upm.edu.my/id/eprint/118626/
http://psasir.upm.edu.my/id/eprint/118626/1/118626.pdf