Automated CNN architecture design with enhanced particle swarm optimization

Arjun Ghosh (), Nanda Dulal Jana () and Subhayu Ghosh ()
Additional contact information
Arjun Ghosh: Department of Computer Science and Engineering, National Institute of Technology Durgapur
Nanda Dulal Jana: Department of Computer Science and Engineering, National Institute of Technology Durgapur
Subhayu Ghosh: Department of Computer Science and Engineering, National Institute of Technology Durgapur

Journal of Heuristics, 2025, vol. 31, issue 4, No 4, 51 pages

Abstract: Abstract Deep convolutional neural networks (CNNs) are powerful deep learning models for tackling various computer vision challenges, particularly image classification. However, designing an optimal CNN model is a complex, labor-intensive, and resource-demanding process that typically requires extensive manual effort and domain-specific knowledge. This paper introduces EPSO-CNN, an efficient framework leveraging particle swarm optimization (PSO) to automatically design optimal CNN architectures for image classification tasks. The proposed method utilizes a modified variable-length encoding scheme for flexible and efficient representation of CNN layers as particles, facilitating rapid architecture construction without conversion overhead. Novel strategies for velocity and position updates are incorporated to enhance search exploration and prevent premature convergence. Batch normalization and dropout techniques are employed to accelerate training and mitigate overfitting. Experimental results on eight widely used image classification datasets show that EPSO-CNN outperforms most of the 26 state-of-the-art models with notably lower error rates, and its superiority is further validated on NAS-Bench-101 and NAS-Bench-201, confirming its competitiveness across standardized NAS evaluation platforms. The best CNN architectures generated by EPSO-CNN are evaluated on facial expression recognition (FER) challenge dataset, showcasing their robustness and generalization ability in real-life application. The findings confirm the efficacy of EPSO-CNN in automating the design of deep CNN architectures, offering a valuable tool for advancing image classification methodologies.

Keywords: Neural Architecture Search (NAS); Convolutional Neural Networks (CNNs); Particle Swarm Optimization (PSO); Image Classification (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10732-025-09570-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joheur:v:31:y:2025:i:4:d:10.1007_s10732-025-09570-5

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10732

DOI: 10.1007/s10732-025-09570-5

Access Statistics for this article

Journal of Heuristics is currently edited by Manuel Laguna

More articles in Journal of Heuristics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().