• Saturday, Oct 17th, 2026

International Journal of Advanced Research in Education and TechnologY(IJARETY)
International, Double Blind-Peer Reviewed & Refereed Journal, Open Access Journal
|Approved by NSL & NISCAIR |Impact Factor: 8.152 | ESTD: 2014|

|Scholarly Open Access Journals, Peer-Reviewed, and Refereed Journal, Impact Factor-8.152 (Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool), Multidisciplinary, Bi-Monthly, Citation Generator, Digital Object Identifier(DOI)|

Article

TITLE A Bio-Inspired Approach to Enhance CNN Performance in Image Classification via PSO-Optimized Hyperparameters
ABSTRACT Deep neural network training must include the optimization of hyperparameters as the selection of the best hyperparameters has a substantial impact on model performance. In this paper, we investigate the paired application of Particle Swarm Optimization (PSO), a bio-inspired method, and Convolutional Neural Networks (CNNs), a deep learning framework, to optimize hyperparameters for image classification tasks. We show that PSO can efficiently search the hyperparameter space, improving CNN performance and reducing the computational load of human hyperparameter tuning.
AUTHOR Dr.V.Valarmathi, Dr.D.R.Medhunhashini Assistant Professor, Department of IT & Cognitive Systems, Sri Krishna Arts and Science College, Coimbatore, Tamil Nadu, India
VOLUME 13
DOI DOI:10.15680/IJARETY.2026.1305003
PDF 3_A Bio-Inspired Approach to Enhance CNN Performance in Image Classification via PSO-Optimized Hyperparameters.pdf
KEYWORDS
References 1. Li, L., Tang, K., & Yao, X. (2020). Self-adaptive dynamic particle swarm optimization. IEEE Transactions on Evolutionary Computation, 24(2), 331-346.
2. Snoeyink, J., & Eberhart, R. (2019). Extended Particle Swarm Optimization for Hyperparameter Selection in Deep Learning. In Proceedings of the 2019 Genetic and Evolutionary Computation Conference (GECCO'19).
3. Zhang, L., Liu, L., Mei, Y., & Zhang, Y. (2020). Weighted PSO with enhanced stochastic ranking for deep neural network training. IEEE Transactions on Evolutionary Computation, 24(4), 715-727.
4. Elsken, T., Metzen, J. H., & Hutter, F. (2019). Neural architecture search: A survey. Journal of Machine Learning Research, 20(55), 1-21.
5. Real, E., Aggarwal, A., Huang, Y., & Le, Q. V. (2019). Regularized evolution for image classifier architecture search. In Proceedings of the 6th International Conference on Learning Representations (ICLR).
6. Li, L., Zhang, L., Mei, Y., & Yao, X. (2020). Efficient hyperparameter optimization for deep learning algorithms using evolutionary algorithms. IEEE Transactions on Evolutionary Computation, 24(5), 877-889.