Application of Evolutionary Algorithms to Enhance the Efficiency of Neural Networks and Machine Learning Algorithms

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.

More by Mekhriddin Nurmamatov

• Lean Quantum Intelligence: A Compact Variational-Circuit Hybrid for Turbofan RUL Prediction with SHAP AttributionComputers · 2026
• Investigation of Vulnerabilities of Machine Learning Models to Adversarial Attacks in Smart Grid Forecasting SystemsAdvances in computational intelligence and robotics book series · 2026
• Capacity-Constrained Multi-robot Task Allocation via Quantum Approximate Optimisation: A Reproducible Benchmark on a Solomon VRPTW C101-Derived InstanceCommunications in computer and information science · 2026
• Forecasting Electrical Load and Renewable Energy Generation Using Machine Learning MethodsAdvances in computational intelligence and robotics book series · 2026