Abstract
The hyperparameters of a convolutional neural network always have been important, because the performance of the convolutional neural network depends largely on them. To find manually the optimal value requires a lot of work, experience, and time. Metaheuristic algorithms are approximate general-purpose search and optimization algorithms, they are used to find a good solution into search space. In the book chapter, the hyperparameters of a convolutional neural network are optimized. A metaheuristic algorithm is used to finds the best solution, that is, the best hyperparameter value for higher accuracy of the convolutional neural network (CNN). The results of four metaheuristic algorithms that have the same objective are compared, which are PSO (Particle Swarm Optimization), ABC (Artificial Bee Colony), ALO (Ant Lion Optimization), and BA (Bat Algorithm). Each algorithm uses the same convolutional neural network architecture as well as the same dataset (MNIST database) also each algorithm is run 30 times to perform the corresponding statistics. Finally, the results of the algorithms are shown.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Teuwen, J., Moriakov, N., Convolutional neural networks, in Handbook of Medical Image Computing and Computer Assisted Intervention (Elsevier, 2019), pp. 481–501
Lopez Pinaya, W.H., Vieira, S., Garcia-Dias, R., Mechelli, A., Convolutional neural networks, in Machine Learning (Elsevier, 2020), pp. 173–191
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition. Proc. IEEE 1–46 (1998)
Krizhevsky A., Sutskever I., Hinton G., ImageNet classification with deep convolutional neural networks. Commun. ACM. 60, 84–90 (2017)
Simonyan, K., Zisserman, A., Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Deepan, P., Sudha, L.R., Object classification of remote sensing image using deep convolutional neural network, in The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems (Elsevier, 2020), pp. 107–120
H. Cui, J. Bai, A new hyperparameters optimization method for convolutional neural networks. Pattern Recogn. Lett. 125, 828–834 (2019). https://doi.org/10.1016/j.patrec.2019.02.009
Loussaief, S., Abdelkrim, A., Convolutional neural network hyper-parameters optimization based on genetic algorithms. Int. J. Adv. Comput. Sci. Appl. 9 (2018)
Y. Wang, H. Zhang, G. Zhang, cPSO-CNN: an efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks. Swarm Evol. Comput. 49, 114–123 (2019). https://doi.org/10.1016/j.swevo.2019.06.002
Lorenzo, P.R., Nalepa, J., Kawulok, M., Ramos, L.S., Pastor, J.R., Particle swarm optimization for hyper-parameter selection in deep neural networks, in GECCO 2017—Proceedings of the 2017 Genetic and Evolutionary Computation Conference (Association for Computing Machinery, Inc, 2017), pp 481–488
Dewancker, I., McCourt, M., Clark, S., Bayesian optimization for machine learning : a practical guidebook. ArXiv abs/1612.04858 (2016)
Bergstra, J., Bengio, Y., Random search for hyper-parameter optimization. J. Machine Learning Res.13, 281–305 (2012)
Frazier, P.I., A tutorial on bayesian optimization. ArXiv abs/1807.02811 (2018)
Cuevas, E., Díaz, M. A method for estimating view transformations from image correspondences based on the harmony search algorithm. Comput. Intell. Neurosci. (2015). https://doi.org/10.1155/2015/434263
D. Oliva, S. Hinojosa, E. Cuevas, G. Pajares, O. Avalos, J. Gálvez, Cross entropy based thresholding for magnetic resonance brain images using Crow Search Algorithm. Expert Syst. Appl. 79, 164–180 (2017). https://doi.org/10.1016/j.eswa.2017.02.042
D. Zaldivar, E. Cuevas, O. Maciel, A. Valdivia, E. Chavolla, D. Oliva, Learning classical and metaheuristic optimization techniques by using an educational platform based on LEGO robots. Int. J. Electr. Eng. Educ. (2019). https://doi.org/10.1177/0020720918822738
Cuevas, E., Barocio Espejo, E., Conde Enríquez, A., Clustering representative electricity load data using a particle swarm optimization algorithm. Stud. Comput. Intell. 187–210 (2019. (Springer)
Avalos, O., Cuevas, E., Gálvez, J. Induction motor parameter identification using a gravitational search algorithm. Computers 5 (2016). https://doi.org/10.3390/computers5020006
E. Cuevas, Artificial Bee Colony (ABC) algorithm and its use in digital image processing. Intel. Artif. 18, 50 (2015). https://doi.org/10.4114/intartif.vol18,issue55,pp.50-68
D. Oliva, E. Cuevas, G. Pajares, Parameter identification of solar cells using artificial bee colony optimization. Energy 72, 93–102 (2014). https://doi.org/10.1016/j.energy.2014.05.011
M. Elhoseny, D. Oliva, V. Osuna-Enciso, A.E. Hassanien, M. Gunasekaran, Parameter identification of two dimensional digital filters using electro-magnetism optimization. Multimedia Tools Appl. 79, 5005–5022 (2020). https://doi.org/10.1007/s11042-018-6095-1
Oliva, D., Hinojosa, S., Demeshko, M.V., Engineering applications of metaheuristics: an introduction. J. Phys. Conf. Ser. (2017). [Institute of Physics Publishing]
Avalos, O., Cuevas, E., Valdivia-González, A., Gálvez, J., Hinojosa, S., Zaldívar, D., Oliva, D., A comparative study of evolutionary computation techniques for solar cells parameter estimation. Computacion y Sistemas 23, 231–256 (2019). https://doi.org/10.13053/CyS-23-1-2881
Dokeroglu, T., Sevinc, E., Kucukyilmaz, T., Cosar, A., A survey on new generation metaheuristic algorithms. Comput. Ind. Eng. 137 (2019). https://doi.org/10.1016/j.cie.2019.106040
Roy, A., Dutta, D., Choudhury, K (2013) Training artificial neural network using particle swarm optimization algorithm. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3(3) (2013)
Garro, B.A., Vázquez, R.A., Designing artificial neural networks using particle swarm optimization algorithms. Comput. Intell. Neurosci. (2015). https://doi.org/10.1155/2015/369298
W. Gómez-Flores, J. Hernández-López, Automatic adjustment of the pulse-coupled neural network hyperparameters based on differential evolution and cluster validity index for image segmentation. Appl. Soft Comput. J. (2019). https://doi.org/10.1016/j.asoc.2019.105547
W.Y. Lee, S.M. Park, K.B. Sim, Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm. Optik 172, 359–367 (2018). https://doi.org/10.1016/j.ijleo.2018.07.044
Aszemi, N.M., Dominic, P.D.D., Hyperparameter optimization in convolutional neural network using genetic algorithms. Int. J. Adv. Comput. Sci. Appl. 10 (2019)
Y. Yoo, Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches ✩. Knowl. Based Syst. 178, 74–83 (2019). https://doi.org/10.1016/j.knosys
Y. Bengio, Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–27 (2009). https://doi.org/10.1561/2200000006
S. Mirjalili, The ant lion optimizer. Adv. Eng. Softw. 83, 80–98 (2015). https://doi.org/10.1016/j.advengsoft.2015.01.010
H. Garg, Solving structural engineering design optimization problems using an artificial bee colony algorithm. J. Ind. Manag. Optim. 10, 777–794 (2014). https://doi.org/10.3934/jimo.2014.10.777
Yang, X.S., A new metaheuristic bat-inspired algorithm, in Studies in Computational Intelligence (2010), pp 65–74
Solano, R., Meléndez, N., Garcia, C., C-PSO: Particle Swarm Optimization by Embedding Coulomb’s Law. Res. Comput. Sci. 147, 311–322 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Gaspar, A., Oliva, D., Cuevas, E., Zaldívar, D., Pérez, M., Pajares, G. (2021). Hyperparameter Optimization in a Convolutional Neural Network Using Metaheuristic Algorithms. In: Oliva, D., Houssein, E.H., Hinojosa, S. (eds) Metaheuristics in Machine Learning: Theory and Applications. Studies in Computational Intelligence, vol 967. Springer, Cham. https://doi.org/10.1007/978-3-030-70542-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-70542-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70541-1
Online ISBN: 978-3-030-70542-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)