Publication: Finding optimal hyperparameters of feedforward neural networks for solving differential equations using a genetic algorithm
Issued Date
2021-01-28
Resource Type
ISSN
17426596
17426588
17426588
Other identifier(s)
2-s2.0-85100813045
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Physics: Conference Series. Vol.1719, No.1 (2021)
Suggested Citation
C. Boonthanawat, C. Boonyasiriwat Finding optimal hyperparameters of feedforward neural networks for solving differential equations using a genetic algorithm. Journal of Physics: Conference Series. Vol.1719, No.1 (2021). doi:10.1088/1742-6596/1719/1/012033 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/79011
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Finding optimal hyperparameters of feedforward neural networks for solving differential equations using a genetic algorithm
Author(s)
Other Contributor(s)
Abstract
In this work, feedforward neural networks are used to solve 2D Laplace equation on rectangular domains. Optimal values of weights and biases of a network are recursively computed during the network training by minimizing a least-squares loss function using data at collocation points to approximate the true solution. The performance of the network largely depends on network architecture and model capability. In this work, an optimal set of hyperparameters is searched on various values of relative error. The genetic algorithm is used to find the optimal activation function, optimization algorithm, and weight initialization. In addition, we also searched for the optimal value of the number of hidden layers for a specific value of total parameters. Numerical results show that we can successfully obtain an optimal set of hyperparameters that is consistent across many values of relative error.