Utilizing Genetic Algorithms for Tuning and Enhancing Hyperparameters of Neural Networks

Bader Awedat (1)
(1) Faculty of Information Technology, Al- Zaytouna University, Tarhuna, Libya

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

Generated from XML file

Authors

Bader Awedat
bader_najep@yahoo.com (Primary Contact)
Awedat ب. (2023). Utilizing Genetic Algorithms for Tuning and Enhancing Hyperparameters of Neural Networks. Journal of Pure & Applied Sciences, 22(3), 108–115. https://doi.org/10.51984/jopas.v22i3.2756

Article Details

Improve of Harmony Search by Scramble Mutation for Global Optimizations Problems

Khamiss M. S. Ahmed, Mahmmoud Hafsaldin Alawan, Fatima Mustafa
Abstract View : 264
Download :217

Applying CST on Medical Datasets

Omar A. A. Shiba
Abstract View : 115
Download :84