Utilizing Genetic Algorithms for Tuning and Enhancing Hyperparameters of Neural Networks
Article Sidebar
-
Genetic algorithm, Hyperparameter optimization, MLP neural network, Classification accuracy, Iris dataset, Handwritten Numeral dataset
Abstract
The present study utilized a genetic algorithm to optimize the hyperparameters of an MLP neural network. The key hyperparameters, including the hidden layer sizes, number of epochs, learning rate, and optimization algorithm, were subjected to optimization using the genetic algorithm. The Iris flower dataset and the handwritten Numeral dataset were employed to evaluate the performance of the optimized model. The results showed significant improvements in the classification accuracy achieved through the genetic algorithm optimization. The Iris dataset yielded a perfect accuracy of 100%, indicating excellent classification performance. Similarly, the handwritten Numeral dataset achieved an accuracy of 94%, demonstrating the effectiveness of the optimized model in recognizing handwritten Numeral. These findings underscore the importance of genetic algorithms in fine-tuning and enhancing the hyperparameters of MLP neural networks. The application of the genetic algorithm resulted in improved performance and increased classification accuracy in both datasets, showcasing the potential of this approach in improving the performance of neural network models.
Full text article
References
[1]-Chen Li, JinZhe Jiang, YaQian Zhao, RenGang Li, EnDong Wang, Xin Zhang, and Kun Zhao "Genetic algorithm based hyper-parameters optimization for transfer convolutional neural network", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 1228512(15 June 2022); https://doi.org/10.1117/12.2637170
[2]-Han, Ji-Hoon; Choi, Dong-Jin; Park, Sang-Uk; Hong, Sun-Ki (2020). "Hyperparameter Optimization Using a Genetic Algorithm Considering Verification Time in a Convolutional Neural Network." Journal of Electrical Engineering & Technology. doi:10.1007/s42835-020-00343-7.
[3]-Erden, C. Genetic algorithm-based hyperparameter optimization of deep learning models for PM2.5 time-series reductionist. J. Environ. Sci. Technol. 20, 2959–2982 (2023). https://doi.org/10.1007/s13762-023-04763-6
[4]-Lee, S.; Kim, J.; Kang, H.; Kang, D.-Y.; Park, J. Genetic Algorithm Based Deep Learning Neural Network Structure and Hyperparameter Optimization. Appl. Sci. 2021, 11, 744. https://doi.org/10.3390/app11020744
[5]-A.E. Eiben and J.E. Smith, "Introduction to Evolutionary Computing, Second Edition," Natural Computing Series, ISSN 1619-7127, Doi: 10.1007/978-3-662-44874-8, 2015.
[6]-Magnitsky, M. (2011). Artificial Intelligence: A Guide to Intelligent Systems (3nd). Pearson Education Limited.
[7]-Sushruta Mishra, Soumya Sahoo, Mamata Das, "Genetic Algorithm: An Efficient Tool for Global Optimization," Advances in Computational Sciences and Technology (ACST), Volume 10, Number 8, 2017, pp. 2201-221.
[8]-Y. LeCun, C. Cortes, and C. Burges, "MNIST handwritten digit database," Retrieved from http://yann.lecun.com/exdb/mnist/, Accessed on 27-1-2023.
[9]-Sahid, A. K., & Khowar, H. (2022). A comparison of artificial neural networks and support vector regression models for forecasting oil prices during the period2000-2022. Journal of Economic and Administrative Research, 61(20), 38-83.
[10]-Iris dataset UCI. (2023). Kaggle. Retrieved on April 11, 2023, from https://www.kaggle.com/datasets/jillanisofttech/iris-dataset-uci.
Authors
Copyright (c) 2023 Journal of Pure & Applied Sciences
This work is licensed under a Creative Commons Attribution 4.0 International License.
In a brief statement, the rights relate to the publication and distribution of research published in the journal of the University of Sebha where authors who have published their articles in the journal of the university of Sebha should how they can use or distribute their articles. They reserve all their rights to the published works, such as (but not limited to) the following rights:
- Copyright and other property rights related to the article, such as patent rights.
- Research published in the journal of the University of Sebha and used in its future works, including lectures and books, the right to reproduce articles for their own purposes, and the right to self-archive their articles.
- The right to enter a separate article, or for a non-exclusive distribution of their article with an acknowledgment of its initial publication in the journal of Sebha University.
Privacy Statement The names and e-mail addresses entered on the Sabha University Journal site will be used for the aforementioned purposes only and for which they were used.