[1]艾玲梅,叶雪娜.基于循环卷积神经网络的目标检测与分类[J].计算机技术与发展,2018,28(02):31-35.[doi:10．3969/j．issn．1673－629X．2018．02．008]
　AI Ling-mei,YE Xuena.Object Detection and Classification Based on Circular Convolutional Neural Network[J].,2018,28(02):31-35.[doi:10．3969/j．issn．1673－629X．2018．02．008]
点击复制

基于循环卷积神经网络的目标检测与分类()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
31-35
栏目:
智能、算法、系统工程
出版日期:
2018-02-10

文章信息/Info

Title:
Object Detection and Classification Based on Circular Convolutional Neural Network
文章编号:
1673－629X(2018)02－0031－05
作者:
艾玲梅; 叶雪娜
陕西师范大学 计算机科学学院，陕西 西安 710119
Author(s):
 AI Ling-mei; YE Xue－na
School of Computer Science，Shaanxi Normal University，Xi’an 710119，China
关键词:
物体检测; 进退法; 黄金分割算法; 随机梯度算法; 神经网络
Keywords:
object detection; advance and retreat method; golden section algorithm; stochastic gradient method; neural network
分类号:
TP311
DOI:
10．3969/j．issn．1673－629X．2018．02．008
文献标志码:
A
摘要:
卷积神经网络模仿人类的视觉识别能力，提取图像目标的显著抽象特征，在图像目标检测与分类的应用上效果良好。在当前比较流行的批量随机梯度训练算法训练卷积神经网络的过程中，当神经元处于饱和状态时，会出现梯度下降缓慢和过度拟合问题，易使神经网络模型训练陷入困难。结合卷积神经网络和循环神经网络的特点，提出了构造浅层循环卷积神经网络，且在训练循环卷积神经网络模型时，分别采用进退法、黄金分割法自适应地改变批量随机梯度下降算法的规范化参数和学习率。实验结果表明，改进算法能够较好地避免梯度下降缓慢和过拟合问题，在训练循环卷积神经网络模型时具有较好的目标检测分类效果和更快的收敛性。
Abstract:
Convolutional neural network simulates human vision recognition and extracts the abstract characteristics significantly of the image target，with better effects on the application of image target detection and classification．In the currently popular training of convolution neural network by batch stochastic gradient algorithm，when neurons in a saturated state，there will be a slow gradient descent and excessive fitting which lead to the difficulties in training of the neural network model．In this paper，we propose a simple circular convolutional neural networks
combined with the characteristics of the convolutional and circular neural networks．In the training of circular convolutional neural network model，advance and retreat method and golden section are used to adaptively change the normalized parameter and the learning rate of batch stochastic gradient descent algorithm．Experiment shows that the proposed algorithm，with a better effect on detection and classification with faster convergence，can avoid the problem of slow gradient decent and excessive fitting to some extent．

相似文献/References:

[1]郑权,刘循,魏海明.基于学习的霍夫变换线段组物体检测算法[J].计算机技术与发展,2014,24(01):26.
　ZHENG Quan,LIU Xun,WEI Hai-ming.An Object Detection Algorithm of Hough Transform Line Segmentation Groups Based on Learning[J].,2014,24(02):26.
[2]汤斯鹏,池鸿源,张培炜,等.深度学习识别光网络单元故障的设计与应用[J].计算机技术与发展,2020,30(05):211.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 040]
　TANG Si-peng,CHI Hong-yuan,ZHANG Pei-wei,et al.Design and Application of Identifying Malfunctions in Optical Network Units Based on Deep Learning[J].,2020,30(02):211.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 040]

更新日期/Last Update: 2018-03-26