Enhancing Efficiency and Regularization in Convolutional Neural Networks: Strategies for Optimized Dropout
Year: 2025
Type: article
Abstract: Background/Objectives: Convolutional Neural Networks (CNNs), while effective in tasks such as image classification and language processing, often experience overfitting and inefficient training due to static, structure-agnostic regularization techniques like traditional dropout. This study aims to address these limitations by proposing a more dynamic and context-sensitive dropout strategy. Methods: We introduce Probabilistic Feature Importance Dropout (PFID), a novel regularization method that assigns dropout rates based on the probabilistic significance of individual features. PFID is integrated with adaptive, structured, and contextual dropout strategies, forming a unified framework for intelligent regularization. Results: Experimental evaluation on standard benchmark datasets including CIFAR-10, MNIST, and Fashion MNIST demonstrated that PFID significantly improves performance metrics such as classification accuracy, training loss, and computational efficiency compared to conventional dropout methods. Conclusions: PFID offers a practical and scalable solution for enhancing CNN generalization and training efficiency. Its dynamic nature and feature-aware design provide a strong foundation for future advancements in adaptive regularization for deep learning models.
Source: AI
DOI: 10.3390/ai6060111
Author: Mehdi Ghayoumi
Institutions: State University of New York, SUNY Canton
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,930
OpenAlex ID: W4410826102