Research on a New Convolutional Neural Network Model Combined With Random Edges Adding

Jin Zhang, Sen Tian, XuanYu Shu, Sheng Chen and LingYu Chen
Additional contact information
Jin Zhang: College of Information Science and Engineering, Hunan Normal University, China
Sen Tian: Mathematics and Statistics, Hunan Normal University, China
XuanYu Shu: Mathematics and Statistics, Hunan Normal University, China
Sheng Chen: College of Information Science and Engineering, Hunan Normal University, China
LingYu Chen: College of Information Science and Engineering, Hunan Normal University, China

International Journal of Distributed Systems and Technologies (IJDST), 2021, vol. 12, issue 1, 67-76

Abstract: It is always a hot and difficult point to improve the accuracy of the convolutional neural network model and speed up its convergence. Based on the idea of the small world network, a random edge adding algorithm is proposed to improve the performance of the convolutional neural network model. This algorithm takes the convolutional neural network model as a benchmark and randomizes backwards and cross layer connections with probability p to form a new convolutional neural network model. The proposed idea can optimize the cross-layer connectivity by changing the topological structure of the convolutional neural network and provide a new idea for the improvement of the model. The simulation results based on Fashion-MINST and cifar10 data set show that the model recognition accuracy and training convergence speed are greatly improved by random edge adding reconstructed models with a probability of p = 0.1.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/IJDST.2021010105 (application/pdf)

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:igg:jdst00:v:12:y:2021:i:1:p:67-76

Access Statistics for this article

International Journal of Distributed Systems and Technologies (IJDST) is currently edited by Nik Bessis

More articles in International Journal of Distributed Systems and Technologies (IJDST) from IGI Global
Bibliographic data for series maintained by Journal Editor ().