基于异构数据集的基准,在cnn中寻找合适的卷积层数的尝试

IF 0.5 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC
V. Romanuke
{"title":"基于异构数据集的基准,在cnn中寻找合适的卷积层数的尝试","authors":"V. Romanuke","doi":"10.2478/ecce-2018-0006","DOIUrl":null,"url":null,"abstract":"Abstract An attempt of finding an appropriate number of convolutional layers in convolutional neural networks is made. The benchmark datasets are CIFAR-10, NORB and EEACL26, whose diversity and heterogeneousness must serve for a general applicability of a rule presumed to yield that number. The rule is drawn from the best performances of convolutional neural networks built with 2 to 12 convolutional layers. It is not an exact best number of convolutional layers but the result of a short process of trying a few versions of such numbers. For small images (like those in CIFAR-10), the initial number is 4. For datasets that have a few tens of image categories and more, initially setting five to eight convolutional layers is recommended depending on the complexity of the dataset. The fuzziness in the rule is not removable because of the required diversity and heterogeneousness","PeriodicalId":42365,"journal":{"name":"Electrical Control and Communication Engineering","volume":"14 1","pages":"51 - 57"},"PeriodicalIF":0.5000,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"An attempt of finding an appropriate number of convolutional layers in cnns based on benchmarks of heterogeneous datasets\",\"authors\":\"V. Romanuke\",\"doi\":\"10.2478/ecce-2018-0006\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract An attempt of finding an appropriate number of convolutional layers in convolutional neural networks is made. The benchmark datasets are CIFAR-10, NORB and EEACL26, whose diversity and heterogeneousness must serve for a general applicability of a rule presumed to yield that number. The rule is drawn from the best performances of convolutional neural networks built with 2 to 12 convolutional layers. It is not an exact best number of convolutional layers but the result of a short process of trying a few versions of such numbers. For small images (like those in CIFAR-10), the initial number is 4. For datasets that have a few tens of image categories and more, initially setting five to eight convolutional layers is recommended depending on the complexity of the dataset. The fuzziness in the rule is not removable because of the required diversity and heterogeneousness\",\"PeriodicalId\":42365,\"journal\":{\"name\":\"Electrical Control and Communication Engineering\",\"volume\":\"14 1\",\"pages\":\"51 - 57\"},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2018-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Electrical Control and Communication Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2478/ecce-2018-0006\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electrical Control and Communication Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2478/ecce-2018-0006","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 8

摘要

摘要试图在卷积神经网络中找到合适数量的卷积层。基准数据集是CIFAR-10、NORB和EEACL26,它们的多样性和异构性必须有助于假设产生该数字的规则的普遍适用性。该规则来自于用2到12个卷积层构建的卷积神经网络的最佳性能。这不是卷积层的确切最佳数量,而是尝试几种版本的卷积层的短过程的结果。对于小图像(如CIFAR-10中的图像),初始数量为4。对于具有几十个或更多图像类别的数据集,建议根据数据集的复杂性,最初设置五到八个卷积层。由于所需的多样性和异质性,规则中的模糊性是不可消除的
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An attempt of finding an appropriate number of convolutional layers in cnns based on benchmarks of heterogeneous datasets
Abstract An attempt of finding an appropriate number of convolutional layers in convolutional neural networks is made. The benchmark datasets are CIFAR-10, NORB and EEACL26, whose diversity and heterogeneousness must serve for a general applicability of a rule presumed to yield that number. The rule is drawn from the best performances of convolutional neural networks built with 2 to 12 convolutional layers. It is not an exact best number of convolutional layers but the result of a short process of trying a few versions of such numbers. For small images (like those in CIFAR-10), the initial number is 4. For datasets that have a few tens of image categories and more, initially setting five to eight convolutional layers is recommended depending on the complexity of the dataset. The fuzziness in the rule is not removable because of the required diversity and heterogeneousness
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Electrical Control and Communication Engineering
Electrical Control and Communication Engineering ENGINEERING, ELECTRICAL & ELECTRONIC-
自引率
14.30%
发文量
0
审稿时长
12 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信