Optimization of deep learning architecture based on multi-path convolutional neural network algorithm
Rattachement africain : cn. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Current multi-stream convolutional neural network (MSCNN) exhibits notable limitations in path cooperation, feature fusion, and resource utilization when handling complex tasks. To enhance MSCNN's feature extraction ability, computational efficiency, and model robustness, this study conducts an in-depth investigation of these architectural deficiencies and proposes corresponding improvements. At present, there are some problems in multi-path architecture, such as isolated information among paths, low efficiency of feature fusion mechanism, and high computational complexity. These issues lead to insufficient performance of the model in robustness indicators such as noise resistance, occlusion sensitivity, and resistance to sample attacks. The architecture also faces challenges in data scalability efficiency and resource scalability requirements. Therefore, this study proposes an optimized model based on a dynamic path cooperation mechanism and lightweight design, innovatively introducing a path attention mechanism and feature-sharing module to enhance information interaction between paths. Self-attention fusion method is adopted to improve the efficiency of feature fusion. At the same time, by combining path selection and model pruning technology, the effective balance between model performance and computational resources demand is realized. The study employs three datasets, Canadian Institute for Advanced Research-10 (CIFAR-10), ImageNet, and Custom Dataset for performance comparison and simulation. The results show that the proposed optimized model is superior to the current mainstream model in many indicators. For example, on the Medical Images dataset, the optimized model's noise robustness, occlusion sensitivity, and sample attack resistance are 0.931, 0.950, and 0.709, respectively. On E-commerce Data, the optimized model's data scalability efficiency reaches 0.969, and the resource scalability requirement is only 0.735, showing excellent task adaptability and resource utilization efficiency. Therefore, the study provides a critical reference for the optimization and practical application of MSCNN, contributing to the application research of deep learning in complex tasks.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Optimization of deep learning architecture based on multi-path convolutional neural network algorithm
- Date Crossref
- 04/06/2025
- Éditeur
- Springer Science and Business Media LLC
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Tianjin University pays non établi dans la noticeUniversité ou école supérieure
-
China United Network Communications Group (China) pays non établi dans la noticeEntreprise
-
Inspur (China) pays non établi dans la noticeEntreprise
-
Beijing Forestry University pays non établi dans la noticeUniversité ou école supérieure
-
Shandong Agricultural University pays non établi dans la noticeUniversité ou école supérieure
-
National Natural Science Foundation of China pays non établi dans la noticeOrganisme public
-
Ltd China United Network Communication Group Co. pays non établi dans la noticeEntreprise
-
School of Microelectronics pays non établi dans la noticeUniversité ou école supérieure
-
College of Environmental Science and Engineering pays non établi dans la noticeUniversité ou école supérieure
-
School of International exchange pays non établi dans la noticeUniversité ou école supérieure
-
Education Foundation of Beijing Central University for Nationalities pays non établi dans la noticeUniversité ou école supérieure
Tianjin University, China United Network Communications Group (China) et Inspur (China), avec 8 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.