Application of Evolutionary Algorithms to Enhance the Efficiency of Neural Networks and Machine Learning Algorithms
Authors:
- 24 March 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 533-537
Abstract
This study examines approaches to hyperparameter optimization in machine learning and deep learning systems using genetic algorithms. Today, the success of neural networks and machine learning algorithms largely depends on the correct tuning of their hyper parameters. Traditional approaches, such as search networks and Bayesian optimization, can sometimes be inefficient for high-dimensional and complex models. This study analyzes the possibility of improving machine learning results by selecting hyper parameters based on the principles of natural evolution of genetic algorithms. The proposed methods are tested on practical problems related to neural networks, and the results of the research on performance indicators reveal opportunities for improving the accuracy and efficiency of predictions in machine learning and neural networks.Keywords
This publication has 18 references indexed in Scilit:
- Assessing the economic-statistical performance of an attribute SVSSI-np control chart based on genetic algorithmsComputers & Industrial Engineering, 2024
- Balancing Pareto Front exploration of Non-dominated Tournament Genetic Algorithm (B-NTGA) in solving multi-objective NP-hard problems with constraintsInformation Sciences, 2024
- Predicting students’ future final exam results using machine learning algorithms: A comparative analysisAIP Conference Proceedings, 2024
- Genetic algorithm application technology in multi-parameter optimization problemsAIP Conference Proceedings, 2024
- Intelligent system of labor market regulation based on the evolutionary modeling of employment2022
- Warehouse accounting automated information system design2022
- Effects of memory and genetic operators on Artificial Bee Colony algorithm for Single Container Loading problemApplied Soft Computing, 2021
- A population perturbation and elimination strategy based genetic algorithm for multi-satellite TT&C scheduling problemSwarm and Evolutionary Computation, 2021
- Comparison and combination of NLPQL and MOGA algorithms for a marine medium-speed diesel engine optimisationEnergy Conversion and Management, 2017
- Genetic algorithms for modelling and optimisationJournal of Computational and Applied Mathematics, 2005