###
:2019,28(7):139-144
本文二维码信息
码上扫一扫!
基于残差的改进卷积神经网络图像分类算法
(华南师范大学 计算机学院, 广州 510631)
Improved CNN Image Classification Algorithm Based on Residuals
(School of Computer Science, South China Normal University, Guangzhou 510631, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 81次   下载 68
投稿时间:2019-01-20    修订日期:2019-02-21
中文摘要: 现有深度残差网络作为一种卷积神经网络的变种,由于其良好的表现,被应用于各个领域,深度残差网络虽然通过增加神经网络深度获得了较高的准确率,但是在相同深度情况下,仍然有其他方式提升其准确率.本文针对深度残差网络使用了三种优化方法:(1)通过卷积网络进行映射实现维度填充;(2)构建基于SELU激活函数的残差模块(3)学习率随迭代次数进行衰减.在数据集Fashion-MNIST上测试改进后的网络,实验结果表明:所提出的网络模型在准确率上优于传统的深度残差网络.
Abstract:The existing deep residual network, as a variant of a convolutional neural network, is used in various fields due to its sound performance. Although the depth residual network obtains higher accuracy by increasing the depth of the neural network, there are still other ways to improve the accuracy at the same depth. In this study, three optimization methods are used to optimize the depth residual network. (1) Dimension filling by mapping through a convolutional network. (2) Building a residual module based on the SELU activation function. (3) Learning rate decays with the number of iterations. Testing the improved network on the dataset Fashion-MNIST, the experimental results show that the proposed network model is superior to the traditional deep residual network in accuracy.
文章编号:     中图分类号:    文献标志码:
基金项目:广东省重大科技专项(2016B030305003)
引用文本:
高磊,范冰冰,黄穗.基于残差的改进卷积神经网络图像分类算法.计算机系统应用,2019,28(7):139-144
GAO Lei,FAN Bing-Bing,HUANG Sui.Improved CNN Image Classification Algorithm Based on Residuals.COMPUTER SYSTEMS APPLICATIONS,2019,28(7):139-144

用微信扫一扫

用微信扫一扫