Work

Adaptive hybrid optimization for backpropagation neural networks in image classification

Year: 2025

Type: article

Abstract: Image classification is essential in artificial intelligence, with applications in medical diagnostics, autonomous navigation, and industrial automation. Traditional training methods like stochastic gradient descent (SGD) often suffer from slow convergence and local minima. This research presents a hybrid Particle Swarm Optimization (PSO)-Genetic Algorithm (GA)-Backpropagation framework to enhance neural network training. By integrating AdaGrad and PSO for weight optimization, GA for refinement, and backpropagation for fine-tuning, the model improves performance. Results show a 97.5% accuracy on MNIST, a 5% improvement over Adam, and 40% faster convergence than SGD. This approach enhances efficiency, accuracy, and generalization, making it valuable for high-dimensional AI tasks.

Source: Proceedings of the Nigerian Society of Physical Sciences

DOI: 10.61298/pnspsc.2025.2.150

Authors: Samuel Essang, Stephen Okeke, Jackson Ante Effiong, Runyi Francis, Sunday E. Fadugba, Augustine Ogbaji Otobi, Jonathan T. Auta, Chikwe F. Chukwuka, Michael O. Ogar-Abang, Aigberemhon Moses

Institutions: Arthur Jarvis University, David Umahi Federal University of Health Sciences Uburu, Topfaith University, Federal Polytechnic Ugep, Ekiti State University, University of Calabar, African Institute of Science and Technology, University of Cross River State

Language: English

Topic: Metaheuristic Optimization Algorithms Research

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4408327712

FWCI: 1.665

Cites:

Cited by: 4

Related to: 10