Research on a New Convolutional Neural Network Model Combined with Random Edges Adding
Abstract
It is always a hot and difficult point to improve the accuracy of convolutional neural network model and speed up its convergence. Based on the idea of small world network, a random edge adding algorithm is proposed to improve the performance of 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 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 aprobability p = 0.1.
Cite
@article{arxiv.2003.07794,
title = {Research on a New Convolutional Neural Network Model Combined with Random Edges Adding},
author = {Xuanyu Shu and Jin Zhang and Sen Tian and Sheng chen and Lingyu Chen},
journal= {arXiv preprint arXiv:2003.07794},
year = {2020}
}
Comments
I am very sorry to request the withdrawal of the manuscript for the following reasons: 1.Uploading this manuscript violates school-related requirements. 2.And at the same time, when the tutor and other authors knew about it, they did not agree and requested to withdraw the manuscript. I hope you can understand and agree to my request