Simplified swarm optimization for hyperparameters of convolutional neural networks

被引:16
|
作者
Yeh, Wei -Chang [1 ]
Lin, Yi-Ping [1 ]
Liang, Yun-Chia [2 ]
Lai, Chyh-Ming [3 ]
Huang, Chia -Ling [4 ]
机构
[1] Natl Tsing Hua Univ, Dept Ind Engn & Engn Management, Integrat & Collaborat Lab, Hsinchu 300, Taiwan
[2] Yuan Ze Univ, Ind Engn & Management, Taoyuan, Taiwan
[3] Natl Def Univ, Management Coll, Taoyuan, Taiwan
[4] Kainan Univ, Dept Int Logist & Transportat Management, Taoyuan 33857, Taiwan
关键词
Machine learning; Image recognition; Convolutional neural networks; Simplified swarm optimization; Hyperparameter optimization;
D O I
10.1016/j.cie.2023.109076
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Convolutional neural networks (CNNs) are widely used in image recognition. Numerous CNN models, such as LeNet, AlexNet, VGG, ResNet, and GoogLeNet, have been developed by increasing the number of layers to improve performance. However, performance deteriorates beyond a certain number of layers. Hence, hyper -parameter optimization is a more efficient way to improve CNNs. To validate this concept, in the present study, an algorithm based on simplified swarm optimization was developed for optimizing the hyperparameters of the simplest CNN model: LeNet. The results of experiments involving the MNIST, Fashion-MNIST, and CIFAR-10 datasets indicated that the accuracy of the proposed algorithm was higher than those of LeNet and PSO-LeNet and that the proposed algorithm can be applied to more complex models such as AlexNet.
引用
收藏
页数:11
相关论文
共 50 条
  • [1] A new hyperparameters optimization method for convolutional neural networks
    Cui, Hua
    Bai, Jie
    [J]. PATTERN RECOGNITION LETTERS, 2019, 125 : 828 - 834
  • [2] On the Selection of Hyperparameters in Convolutional Neural Networks
    Wang, Donglin
    Wu, Qiang
    [J]. 2021 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI 2021), 2021, : 1728 - 1731
  • [3] Efficient Optimization of Convolutional Neural Networks using Particle Swarm Optimization
    Yamasaki, Toshihiko
    Honma, Takuto
    Aizawa, Kiyoharu
    [J]. 2017 IEEE THIRD INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM 2017), 2017, : 70 - 73
  • [4] Optimizing Convolutional Neural Network Hyperparameters by Enhanced Swarm Intelligence Metaheuristics
    Bacanin, Nebojsa
    Bezdan, Timea
    Tuba, Eva
    Strumberger, Ivana
    Tuba, Milan
    [J]. ALGORITHMS, 2020, 13 (03)
  • [5] Automatic Optimization of Hyperparameters for Deep Convolutional Neural Networks: Grid Search Enhanced with Coordinate Ascent
    Song, Qingqing
    Xia, Shaoliang
    Wu, Zhen
    [J]. PROCEEDINGS OF 2024 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE AND DIGITAL APPLICATIONS, MIDA2024, 2024, : 300 - 306
  • [6] Convolutional Neural Network Hyperparameters Optimization for Facial Emotion Recognition
    Vulpe-Grigorasi, Adrian
    Grigore, Ovidiu
    [J]. 2021 12TH INTERNATIONAL SYMPOSIUM ON ADVANCED TOPICS IN ELECTRICAL ENGINEERING (ATEE), 2021,
  • [7] Hyperparameter Optimization for Convolutional Neural Networks using the Salp Swarm Algorithm
    Abdulsaed, Entesar H.
    Alabbas, Maytham
    Khudeyer, Raidah S.
    [J]. Informatica (Slovenia), 2023, 47 (09): : 133 - 144
  • [8] PBIL for Optimizing Hyperparameters of Convolutional Neural Networks and STL Decomposition
    Vasco-Carofilis, Roberto A.
    Gutierrez-Naranjo, Miguel A.
    Cardenas-Montes, Miguel
    [J]. HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, HAIS 2020, 2020, 12344 : 147 - 159
  • [9] Particle Swarm Optimization for Automatically Evolving Convolutional Neural Networks for Image Classification
    Lawrence, Tom
    Zhang, Li
    Lim, Chee Peng
    Phillips, Emma-Jane
    [J]. IEEE ACCESS, 2021, 9 : 14369 - 14386
  • [10] Optimization of convolutional neural network hyperparameters for automatic classification of adult mosquitoes
    Motta, Daniel
    Bandeira Santos, Alex Alisson
    Souza Machado, Bruna Aparecida
    Ribeiro-Filho, Otavio Goncalvez Vicente
    Arriaga Camargo, Luis Octavio
    Valdenegro-Toro, Matias Alejandro
    Kirchner, Frank
    Badaro, Roberto
    [J]. PLOS ONE, 2020, 15 (07):