首页 | 本学科首页   官方微博 | 高级检索  
     检索      

卷积神经网络复杂性质与准确率的关系研究
引用本文:王光波,孙仁诚,隋毅,邵峰晶.卷积神经网络复杂性质与准确率的关系研究[J].复杂系统与复杂性科学,2021(2):60-65.
作者姓名:王光波  孙仁诚  隋毅  邵峰晶
作者单位:青岛大学计算机科学技术学院
基金项目:国家自然科学青年基金(41706198)。
摘    要:卷积神经网络的结构也会对其性能造成影响,设计卷积神经网络更多的是依靠经验和强大的算力,如何设计出性能更好的卷积神经网络目前缺少有效的理论支撑。为了解决这一问题,在分析典型卷积神经网络拓扑复杂性的基础上,为快速实现满足给定复杂性特征的卷积神经网络,给出了由复杂网络拓扑到卷积神经网络的生成算法,通过建立系列不同拓扑特征的卷积神经网络,采用Cifar10和Cifar100数据集分析了平均聚集系数、平均路径长度、图密度、模块度等拓扑性质对卷积神经网络识别有效性的影响关系。实验表明在神经网络的参数数量基本相等的情况下,平均聚类系数会对卷积神经网络的性能产生影响。最终得到结论在统计意义上,平均聚集系数小的网络结构会有更好的性能表现,这为进一步设计出更好的卷积神经网络提供了理论依据。

关 键 词:卷积神经网络  拓扑结构  平均聚集系数  准确率

On the Relationship Between the Complexity and Accuracy of Convolutional Neural Networks
Authors:WANG Guangbo  SUN Rencheng  SUI Yi  SHAO Fengjing
Institution:(School of Computer Science and Technology,Qingdao University,Qingdao 266071,China)
Abstract:The structure of the convolutional neural network will also affect its performance.The design of the convolutional neural network relies more on experience and powerful computing power.How to design a neural network with better performance lacks effective theoretical support.In order to solve this problem,based on the analysis of the complexity of the typical convolutional neural network topology,in order to quickly realize the convolutional neural network that meets the given complexity characteristics,the generation from complex network topology to convolutional neural network is given.The algorithm,through the establishment of a series of convolutional neural networks with different topological features,uses the Cifar10 and Cifar100 data sets to analyze the relationship between the average clustering coefficient,average path length,graph density,modularity and other topological properties on the recognition effectiveness of the convolutional neural network.Experiments show that when the number of parameters of the neural network is basically equal,the average clustering coefficient will affect the performance of the convolutional neural network.The final conclusion is that in a statistical sense,a network structure with a small average clustering coefficient will have better performance,which provides a theoretical basis for further designing a better convolutional neural network.
Keywords:convolutional neural network  topology  average clustering coefficient  accuracy
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号