Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Optimizing deep learning models from multi-objective perspective via Bayesian optimization

IAES International Journal of Artificial Intelligence · Vol. 14 No. 2 (2025) · hlm. 1420–1429

DOI
10.11591/ijai.v14.i2.pp1420-1429
ISSN
2252-8938, 2089-4872
Terbit
2025-04-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Optimizing hyperparameters is crucial for enhancing the performance of deep learning (DL) models. The process of configuring optimal hyperparameters, known as hyperparameter tuning, can be performed using various methods. Traditional approaches like grid search and random search have significant limitations. In contrast, Bayesian optimization (BO) utilizes a surrogate model and an acquisition function to intelligently navigate the hyperparameter space, aiming to provide deeper insights into performance disparities between naïve and advanced methods. This study evaluates BO's efficacy compared to baseline methods such as random search, manual search, and grid search across multiple DL architectures, including multi-layer perceptron (MLP), convolutional neural network (CNN), and LeNet, applied to the Modified National Institute of Standards and Technology (MNIST) and CIFAR-10 datasets. The findings indicate that BO, employing the tree-structured parzen estimator (TPE) search method and expected improvement (EI) acquisition function, surpasses alternative methods in intricate DL architectures such as LeNet and CNN. However, grid search shows superior performance in smaller DL architectures like MLP. This study also adopts a multi-objective (MO) perspective, balancing conflicting performance objectives such as accuracy, F1 score, and model size (parameter count). This MO assessment offers a comprehensive understanding of how these performance metrics interact and influence each other, leading to more informed hyperparameter tuning decisions.

Kata kunci

Jaringan kolaborasi para penulis

36 penulis · 98 tautan kepenulisan bersama · 13 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universiti Teknologi MARA
  • HELP University
  • State University of Semarang
  • Universiti Malaysia Pahang Al-Sultan Abdullah
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Nurbaity SabriUniversiti Teknologi MARA4
Nor Azura Md GhaniUniversiti Teknologi MARA3
Raseeda HamzahUniversiti Teknologi MARA3
Syed Mohd Zahid Syed Zainal AriffinUniversiti Teknologi MARA2
Raihah AminuddinUniversiti Teknologi MARA2
Nur Nabilah Abu MangshorUniversiti Teknologi MARA2
Saadi Bin Ahmad KamaruddinHELP University2
Zaidah IbrahimUniversiti Teknologi MARA2
Marshima Mohd RosliUniversiti Teknologi MARA1
Xiaoling GaoUniversiti Teknologi MARA1
Muhammad Izzad RamliUniversiti Teknologi MARA1
Budi SunarkoState University of Semarang1
Nur Afiqah Mohd FuadUniversiti Teknologi MARA1
Ruiyun QiuUniversiti Teknologi MARA1
Siti Khatijah Nor Abdul RahimUniversiti Teknologi MARA1
Nor Diana AhmadUniversiti Teknologi MARA1
Rosniza RoslanUniversiti Teknologi MARA1
Nurul Shafekah KassimUniversiti Teknologi MARA1
Nurul Amirah ZulkifliUniversiti Teknologi MARA1
Anis Amilah ShariUniversiti Teknologi MARA1
Mohd Rahmat Mohd NoordinUniversiti Teknologi MARA1
Azlee ZabidiUniversiti Malaysia Pahang Al-Sultan Abdullah1
Iylia Ashiqin Abdul MajidUniversiti Teknologi MARA1
Khyrina Airin Fariza Abu SamahUniversiti Teknologi MARA1
Nurul Amira Mohd AliUniversiti Teknologi MARA1
Hazrita Ab RahimHELP University1
Ismail MusirinUniversiti Teknologi MARA1
Muhammad Fareez RashdanUniversiti Teknologi MARA1
Nor Masri SahriUniversiti Teknologi MARA1
Norizah ArdiUniversiti Teknologi MARA1
Izzad RamliUniversiti Teknologi MARA1
Gehad Saleh Ahmed MohammedUniversiti Teknologi MARA1
Norizan Mat DiahUniversiti Teknologi MARA1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Optimizing deep learning models from multi-objective perspective via Bayesian optimization</dc:title>
	<dc:creator>Mohamad Rom, Abdul Rahman</dc:creator>
	<dc:creator>Jamil, Nursuriati</dc:creator>
	<dc:creator>Ibrahim, Shafaf</dc:creator>
	<dc:subject xml:lang="en-US"></dc:subject>
	<dc:subject xml:lang="en-US">Bayesian optimization; Convolutional neural network; Deep learning; Hyperparameter tuning; LeNeT; Multilayer perceptron;</dc:subject>
	<dc:description xml:lang="en-US">Optimizing hyperparameters is crucial for enhancing the performance of deep learning (DL) models. The process of configuring optimal hyperparameters, known as hyperparameter tuning, can be performed using various methods. Traditional approaches like grid search and random search have significant limitations. In contrast, Bayesian optimization (BO) utilizes a surrogate model and an acquisition function to intelligently navigate the hyperparameter space, aiming to provide deeper insights into performance disparities between naïve and advanced methods. This study evaluates BO's efficacy compared to baseline methods such as random search, manual search, and grid search across multiple DL architectures, including multi-layer perceptron (MLP), convolutional neural network (CNN), and LeNet, applied to the Modified National Institute of Standards and Technology (MNIST) and CIFAR-10 datasets. The findings indicate that BO, employing the tree-structured parzen estimator (TPE) search method and expected improvement (EI) acquisition function, surpasses alternative methods in intricate DL architectures such as LeNet and CNN. However, grid search shows superior performance in smaller DL architectures like MLP. This study also adopts a multi-objective (MO) perspective, balancing conflicting performance objectives such as accuracy, F1 score, and model size (parameter count). This MO assessment offers a comprehensive understanding of how these performance metrics interact and influence each other, leading to more informed hyperparameter tuning decisions.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US">Ministry of Higher Education Malaysia (MoHE) and Universiti Teknologi MARA</dc:contributor>
	<dc:date>2025-04-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/25546</dc:identifier>
	<dc:identifier>10.11591/ijai.v14.i2.pp1420-1429</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 14, No 2: April 2025; 1420-1429</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v14.i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/25546/14478</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Institute of Advanced Engineering and Science</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>