[1]蔡 楠,李 萍.基于 KPCA 初始化卷积神经网络的方法[J].计算机技术与发展,2019,29(07):76-79.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 015]
　CAI Nan,LI Ping.Method of Initializing Convolution Neural Network Based on KPCA[J].,2019,29(07):76-79.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 015]
点击复制

基于 KPCA 初始化卷积神经网络的方法()
分享到：

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

卷:
29
期数:
2019年07期
页码:
76-79
栏目:
智能、算法、系统工程
出版日期:
2019-07-10

文章信息/Info

Title:
Method of Initializing Convolution Neural Network Based on KPCA
文章编号:
1673-629X(2019)07-0076-04
作者:
蔡 楠; 李 萍
宁夏大学 物理与电子电气工程学院,宁夏 银川 750021
Author(s):
CAI Nan; LI Ping
School of Physics,Electronic and Electrical Engineering,Ningxia University,Yinchuan 750021,China
关键词:
卷积神经网络; 卷积核初始化; 主成分分析; 核主成分分析; MNIST
Keywords:
convolution neural network; convolution kernel initialization; PCA; KPCA; MNIST
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 07. 015
摘要:
为了解决卷积神经网络中卷积核不能得到有效初始化,导致网络训练难度增加,使网络收敛速度过慢的问题,提出了一种基于 KPCA 初始化卷积核的方法(KPCA-CNN)。 该方法首先创建一个与卷积核大小相同的感受野对每个卷积层第一次输入的所有图像进行滑动采样,采样后的数据经过 KPCA 处理提取主成分,初始化卷积核。 与 PCA 相比,KPCA对图像中的非线性特征有较好的提取能力,所提取的主成分中包含了输入图像的非线性特征,能够更加有效地初始化卷积核,从而降低网络的训练难度,使网络收敛速度变快。 分别将 PCA 初始卷积核方法和 KPCA 初始化卷积核方法应用在MNIST 手写数字识别上进行实验仿真,结果表明 KPCA 初始化卷积核的方法增加了网络的准确率,加快了网络的收敛速度。
Abstract:
In order to solve the problem that convolution neural network cannot initialize convolution kernel effectively,leading to increase of difficulty in network training and slow convergence speed of network,we propose a method based on KPCA initialization convolution kernel (KPCA-CNN). Firstly,a receptive field with the same size of convolution kernel is created for sliding sampling to all images first input in each convolution layer. Then the sampled data are extracted by KPCA,and the convolution kernel is initialized. Compared with PCA,KPCA has a better capacity to extract the nonlinear features in the image. The extracted principal components contain the nonlinear features of the input image and can initialize the convolution kernel more effectively,thus reducing the training difficulty of the network and making the network convergence faster. The PCA and KPCA-CNN are applied to the MNIST handwritten digit recognition to carry out the experimental simulation,which shows that KPCA-CNN increases the accuracy of the network and speeds up the convergence of the network.

相似文献/References:

[1]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(07):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[2]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(07):31.
[3]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(07):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[4]郭子琰,舒心,刘常燕,等.基于ReLU 函数的卷积神经网络的花卉识别算法[J].计算机技术与发展,2018,28(05):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
　GUO Ziyan,SHU Xin,LIU Changyan,et al.A Recognition Algorithm of Flower Based on Convolution Neural Network with ReLU Function[J].,2018,28(07):154.[doi:10．3969/j．issn．1673－629X．2018．05．035]
[5]缪宇杰,吴智钧,宫 婧.基于3D 卷积的视频错帧筛选方法[J].计算机技术与发展,2018,28(05):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
　MIAO Yu-jie,WU Zhi-jun,GONG Jing.A Wrong Temporal-order Frames Identification Method Based on 3D Convolution[J].,2018,28(07):179.[doi:10.3969/ j. issn.1673-629X.2018.05.040]
[6]吴玉枝,吴志红,熊运余.基于卷积神经网络的小样本车辆检测与识别[J].计算机技术与发展,2018,28(06):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
　WU Yu-zhi,WU Zhi-hong,XIONG Yun-yu.Vehicle Detection and Recognition of a Few Samples Based on Convolutional Neural Network[J].,2018,28(07):1.[doi:10.3969/ j. issn.1673-629X.2018.06.001]
[7]李相桥,李晨,田丽华,等.卷积神经网络并行训练的优化研究[J].计算机技术与发展,2018,28(08):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
　LI Xiang-qiao,LI Chen,TIAN Li-hua,et al.Research on Optimization of Parallel Training for Convolution Neural Network[J].,2018,28(07):12.[doi:10.3969/ j. issn.1673-629X.2018.08.003]
[8]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(07):11.
[9]河海大学 计算机与信息学院,江苏 南京 0098.卷积网络的无监督特征提取对人脸识别的研究[J].计算机技术与发展,2018,28(06):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
　DU Bai-sheng.Research on Unsupervised Feature Extraction Based on Convolutional Neural Network for Face Recognition[J].,2018,28(07):17.[doi:10.3969/ j. issn.1673-629X.2018.06.004]
[10]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(07):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]

更新日期/Last Update: 2019-07-10