Low-Overhead Learning: Quantized Shallow Neural Networks at the Service of Genetic Algorithm Optimization
Source abstract
Abstract
Online parameter tuning significantly enhances the performance of optimization algorithms by dynamically adjusting mutation and crossover rates. However, current approaches often suffer from high computational costs and limited adaptability to complex and dynamic fitness landscapes, particularly when machine learning methods are employed. This work proposes a quantized shallow neural network (SNN) as an efficient learning-based component for dynamically adjusting the mutation and crossover rates of a genetic algorithm (GA). By leveraging runtime-generated data and applying quantization techniques like Quantization-aware Training (QaT) and Post-training Quantization (PtQ), the proposed approach reduces computational overhead while maintaining competitive performance. Experimental evaluation on 15 continuous benchmark functions demonstrates that the quantized SNN achieves high-quality solutions while significantly reducing execution time compared to alternative shallow learning methods. This study highlights the potential of quantized SNNs to balance efficiency and performance, broadening the applicability of shallow learning in optimization.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Metaheuristic Optimization Algorithms Research · Machine Learning and Data Classification · Advanced Multi-Objective Optimization Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso, Valparaíso 2362807, Chile
References (25)
Show source-provided references
1. Vega, E., Lemus-Romani, J., Soto, R., Crawford, B., Löffler, C., Peña, J., and Talbi, E.G. (2024). Autonomous Parameter Balance in Population-Based Approaches: A Self-Adaptive Learning-Based Strategy. Biomimetics, 9.10.3390/biomimetics9020082 ↗
2. Hussain, W., Mushtaq, M.F., Shahroz, M., Akram, U., Ghith, E.S., Tlija, M., Kim, T.H., and Ashraf, I. (2025). Ensemble genetic and CNN model-based image classification by enhancing hyperparameter tuning. Sci. Rep., 15.10.1038/s41598-024-76178-3 ↗
3. A survey: From shallow to deep machine learning approaches for blood pressure estimation using biosensors10.1016/j.eswa.2022.116788 ↗
4. Vega, E., Soto, R., Crawford, B., Peña, J., and Castro, C. (2021). A learning-based hybrid framework for dynamic balancing of exploration-exploitation: Combining regression analysis and metaheuristics. Mathematics, 9.10.3390/math9161976 ↗
5. Predicting population size and termination criteria in metaheuristics: A case study based on spotted hyena optimizer and crow search algorithm10.1016/j.asoc.2022.109513 ↗
6. Meir, Y., Tevet, O., Tzach, Y., Hodassman, S., Gross, R.D., and Kanter, I. (2023). Efficient shallow learning as an alternative to deep learning. Sci. Rep., 13.10.1038/s41598-023-32559-8 ↗
7. Biologically plausible deep learning—But how far can we go with shallow networks?10.1016/j.neunet.2019.06.001 ↗
8. Automatically designing CNN architectures using the genetic algorithm for image classification10.1109/TCYB.2020.2983860 ↗
9. Adaptive probabilities of crossover and mutation in genetic algorithms10.1109/21.286385 ↗
10. On hyperparameter optimization of machine learning algorithms: Theory and practice10.1016/j.neucom.2020.07.061 ↗
11. A Genetic Algorithm based Three HyperParameter optimization of Deep Long Short Term Memory (GA3P-DLSTM) for Predicting Electric Vehicles energy consumption10.1016/j.compeleceng.2025.110185 ↗
12. Zebari, R.R., Zeebaree, S.R., Rashid, Z.N., Shukur, H.M., Alkhayyat, A., and Sadeeq, M.A. (2021, January 7–10). A Review on Automation Artificial Neural Networks Based on Evolutionary Algorithms. Proceedings of the 2021 14th International Conference on Developments in eSystems Engineering (DeSE), Sharjah, United Arab Emirates.10.1109/DeSE54285.2021.9719492 ↗
13. An optimized optical diffractive deep neural network with OReLU function based on genetic algorithm10.1016/j.optlastec.2022.109104 ↗
14. MNIST-MIX: A multi-language handwritten digit recognition dataset10.1088/2633-1357/abad0e ↗
15. Intelligent prediction and optimization of ground settlement induced by shield tunneling construction10.1016/j.tust.2025.106486 ↗
16. PATSMA: Parameter Auto-tuning for Shared Memory Algorithms10.1016/j.softx.2024.101789 ↗
17. Comparative analysis of rate of penetration prediction and optimization in deep wells using real-time continuous stacked generalization ensemble learning: A case study in Shunbei10.1016/j.geoen.2025.213674 ↗
18. Mixed-integer linear programming and constraint programming formulations for solving distributed flexible job shop scheduling problem10.1016/j.cie.2020.106347 ↗
19. A linear programming approach for robust network revenue management in the airline industry10.1016/j.jairtraman.2020.101979 ↗
20. Wong, E.Y., and Ling, K.K. (2020, January 27–29). A Mixed Integer Programming Approach to Air Cargo Load Planning with Multiple Aircraft Configurations and Dangerous goods. Proceedings of the 2020 7th International Conference on Frontiers of Industrial Engineering (ICFIE), Singapore.10.1109/ICFIE50845.2020.9266727 ↗
21. A Hybrid Optimization Algorithm for a Multi-Objective Aircraft Loading Problem with Complex Constraints10.1109/ACCESS.2025.3545478 ↗
22. Can shallow neural networks beat the curse of dimensionality? A mean field training perspective10.1109/TAI.2021.3051357 ↗
23. Learnability and robustness of shallow neural networks learned by a performance-driven BP and a variant of PSO for edge decision-making10.1007/s00521-021-06019-1 ↗
24. Improved dropout for shallow and deep learning
25. Barrera-García, J., Cisternas-Caneo, F., Crawford, B., Soto, R., Becerra-Rozas, M., Giachetti, G., and Monfroy, E. (2024, January 21–25). Enhancing Reptile Search Algorithm Performance for the Knapsack Problem with Integration of Chaotic Map. Proceedings of the Mexican International Conference on Artificial Intelligence, Tonantzintla, Mexico.10.1007/978-3-031-75543-9_6 ↗