Article(id=1242140538514780346, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1242140525369831525, articleNumber=null, orderNo=12, doi=10.3981/j.issn.1000-7857.2023.13.010, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1658073600000, receivedDateStr=2022-07-18, revisedDate=1675699200000, revisedDateStr=2023-02-07, acceptedDate=null, acceptedDateStr=null, onlineDate=1691720709757, onlineDateStr=2023-08-11, pubDate=1689177600000, pubDateStr=2023-07-13, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1691720709757, onlineIssueDateStr=2023-08-11, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774078982234, creator=sys-migrate, updateTime=1774078982234, updator=sys-migrate, issue=Issue{id=1242140525369831525, tenantId=1146029695717560320, journalId=1146031591421210625, year='2023', volume='41', issue='13', pageStart='1', pageEnd='128', issueExtLink='null', onlineDate='null', pubDate='1689177600000', pubDateStr='2023-07-13', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=3, issueType=-1, specialIssue=null, createTime=1774078979100, creator='sys-migrate', updateTime=1774078979100, updator='sys-migrate', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=100, endPage=108, ext={EN=ArticleExt(id=1242140542910410980, articleId=1242140538514780346, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=Batch-attention: A method for reconciling overfitting and underfitting in deep learning, columnId=1150494644690366681, journalTitle=Science & Technology Review, columnName=Papers, runingTitle=null, highlight=null, articleAbstract=In the process of deep learning network training, most existing methods aim to improve the model effect focus on the network. However, to improve the effect and accuracy of the model it is necessary to pay attention to the characteristics of the data. In this paper, batch-attention, a new training framework for deep learning model, is proposed, which changes the original training method from the data level. It is shown that the method can coordinate overfitting and underfitting of the deep learning model. Experimental comparisons using Resnet34, TNT and efficientnet-b7 on Cifar10 and Cifar100 data sets respectively prove that the batch-attention model has improved both accuracy and F1-score in the test set compared with the benchmark model. In addition, the mechanism of batch-attention is further analyzed in the follow-up experiment., authors=HU Hanqing, LI Zhengxun, WU Zhunan, authorsList=HU Hanqing, LI Zhengxun, WU Zhunan, authorCompany=School of Economics and Management,Beijing Information Science & Technology University, Beijing 100192,China, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=4eEk0baCGoBP5hAxhHoXIw==, pdfFileSize=1974438, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1242140541664698986, articleId=1242140538514780346, tenantId=1146029695717560320, journalId=1146031591421210625, language=CN, title=Batch-attention:深度学习中一种新的协调过拟合与欠拟合的方法, columnId=1242117055294537731, journalTitle=科技导报, columnName=论文, runingTitle=null, highlight=null, articleAbstract=在深度学习网络训练的过程中,现有大多数提升模型效果的方法都集中在网络上,要提升模型的效果与准确率,就须关注数据的特性。提出了一种新的深度学习模型训练框架Batch-attention,从数据层面出发,改变了原有训练方式,经实验证明可以协调深度学习模型的过拟合与欠拟合。通过在Cifar10与Cifar100数据集上分别采用 Resnet34、Transformer和efficientnet-b7进行实验对比,证明了采用Batch-attention的模型相对于基准模型,在测试集上的准确率与F1-score均有一定提升。在测试实验中,进一步分析了Batch-attention的作用机制。, authors=胡涵清,李政勋,吴竹南, authorsList=胡涵清,李政勋,吴竹南, authorCompany=北京信息科技大学经济管理学院,北京 100192, correspAuthors=null, authorNote=胡涵清,副教授,研究方向为大数据分析与挖掘、机器学习算法等,电子信箱:hanqinghu@bistu.edu.cn, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=g41J1LlbMdymLhkE3iWw3Q==, pdfFileSize=1974438, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=北京信息科技大学“促进同校分类发展——经管学院专业学位点与研究生教育改革”项目)}, authors=null, keywords=[Keyword(id=1242140541152993892, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1242140541257851494, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=CN, orderNo=1, keyword=过拟合), Keyword(id=1242140541345931879, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=CN, orderNo=1, keyword=注意力机制), Keyword(id=1242140541429817960, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=CN, orderNo=1, keyword=有监督学习), Keyword(id=1242140541517898345, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=CN, orderNo=1, keyword=机器学习), Keyword(id=1242140542306431193, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1242140542386122972, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=EN, orderNo=1, keyword=overfitting), Keyword(id=1242140542520340701, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=EN, orderNo=1, keyword=attention mechanism), Keyword(id=1242140542612615391, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=EN, orderNo=1, keyword=supervised learning), Keyword(id=1242140542709084386, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1242140538514780346, language=EN, orderNo=1, keyword=machine learning)], refs=null, funds=null, companyList=null, figs=null, attaches=null, journal=Journal(id=1125356956822126595, delFlag=0, nameCn=科技导报, nameEn=Science & Technology Review, nameHistory1=null, nameHistory2=null, issn=1000-7857, eissn=, cn=11-1421/N, coden=null, periodic=3, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=wfghvu3bhh/dKxuZ+ucVHA==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Rev, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1774230116083, createdBy=null, updatedBy=13041195026, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=wfghvu3bhh/dKxuZ+ucVHA==, picEn=yjSfclmpNm7ihn9NbTZ69g==, jcr=null, cjcr=null, exts=[JournalExt(id=1242774439910290156, language=CN, name=科技导报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国科学技术协会, publishedBy=科技导报社, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjdb.org/CN/home, createdTime=1774230116107, updatedTime=1774230116107, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/CN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.cast.org.cn/webm, submissionEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionReviewUrl=https://kjdbauthor.cast.org.cn/webm, submissionCeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionAeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, option={"copyright":""}), JournalExt(id=1242774439960621805, language=EN, name=Science & Technology Review, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjdb.org/EN/home, createdTime=1774230116119, updatedTime=1774230116119, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/EN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031591421210625, websiteList=[Website(id=1146104741081231361, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kjdb/CN, language=CN, createTime=1751182263881, createBy=18614031015, updateTime=1751778001962, updateBy=18614031015, name=科技导报, tplId=1146099689490845704, title=科技导报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148021146403992296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=articleTextType, value=kx, createTime=1751639170504, updateTime=1751639170504, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146378826469, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=banner, value=null, createTime=1751639170498, updateTime=1751639170498, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146366243556, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1751639170495, updateTime=1751639170495, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146395603687, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751639170502, updateTime=1751639170502, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146387215078, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751639170500, updateTime=1751639170500, creator=18614031015, updator=18614031015)]), Website(id=1146105254833139715, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kjdb/EN, language=EN, createTime=1751182386363, createBy=18614031015, updateTime=1753500121937, updateBy=18614031015, name=科技导报, tplId=1146101810881728533, title=Science & Technology Review, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155838567709528217, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=articleTextType, value=kx, createTime=1753502988984, updateTime=1753502988984, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567692750998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=banner, value=null, createTime=1753502988980, updateTime=1753502988980, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567688556693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1753502988979, updateTime=1753502988979, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567705333912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic, createTime=1753502988983, updateTime=1753502988983, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567701139607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1753502988982, updateTime=1753502988982, creator=18614031015, updator=18614031015)])], journalTitle=科技导报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Science & Technology Review, journalPhotoCn=wfghvu3bhh/dKxuZ+ucVHA==, journalPhotoEn=yjSfclmpNm7ihn9NbTZ69g==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=0.91, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=null, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2023.13.010, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/10.3981/j.issn.1000-7857.2023.13.010, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/PDF/10.3981/j.issn.1000-7857.2023.13.010, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/PDF/10.3981/j.issn.1000-7857.2023.13.010, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=0, orderTime=1689177600000, fullTextJson=null, articleText=null, reference=null)
科技导报
| 论文 2023, 41(13): 100-108
Batch-attention:深度学习中一种新的协调过拟合与欠拟合的方法
全屏
胡涵清,李政勋,吴竹南
作者信息
Batch-attention: A method for reconciling overfitting and underfitting in deep learning
Affiliations
出版时间: 2023-07-13
doi: 10.3981/j.issn.1000-7857.2023.13.010
文章导航
在深度学习网络训练的过程中,现有大多数提升模型效果的方法都集中在网络上,要提升模型的效果与准确率,就须关注数据的特性。提出了一种新的深度学习模型训练框架Batch-attention,从数据层面出发,改变了原有训练方式,经实验证明可以协调深度学习模型的过拟合与欠拟合。通过在Cifar10与Cifar100数据集上分别采用 Resnet34、Transformer和efficientnet-b7进行实验对比,证明了采用Batch-attention的模型相对于基准模型,在测试集上的准确率与F1-score均有一定提升。在测试实验中,进一步分析了Batch-attention的作用机制。
深度学习
/
过拟合
/
注意力机制
/
有监督学习
/
机器学习
In the process of deep learning network training, most existing methods aim to improve the model effect focus on the network. However, to improve the effect and accuracy of the model it is necessary to pay attention to the characteristics of the data. In this paper, batch-attention, a new training framework for deep learning model, is proposed, which changes the original training method from the data level. It is shown that the method can coordinate overfitting and underfitting of the deep learning model. Experimental comparisons using Resnet34, TNT and efficientnet-b7 on Cifar10 and Cifar100 data sets respectively prove that the batch-attention model has improved both accuracy and F1-score in the test set compared with the benchmark model. In addition, the mechanism of batch-attention is further analyzed in the follow-up experiment.
deep learning
/
overfitting
/
attention mechanism
/
supervised learning
/
machine learning
胡涵清,李政勋,吴竹南.
Batch-attention:深度学习中一种新的协调过拟合与欠拟合的方法.
科技导报,
2023
, 41
(13)
: 100
-108
.
DOI: 10.3981/j.issn.1000-7857.2023.13.010
HU Hanqing, LI Zhengxun, WU Zhunan.
Batch-attention: A method for reconciling overfitting and underfitting in deep learning[J].
Science & Technology Review ,
2023
, 41
(13)
: 100
-108
.
DOI: 10.3981/j.issn.1000-7857.2023.13.010
2023年第41卷第13期
PDF下载
279
52
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2023.13.010
接收时间:2022-07-18
首发时间:2023-08-11
出版时间:2023-07-13
收稿日期:2022-07-18
修回日期:2023-02-07
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2023.13.010
复制链接
引用本文
BibTeX
2种不同金属材料的力学参数
科 Family 属数 Number of genus 种数 Number of species 占总种数比例 Percentage of total species (%) 属 Genus 种数 Number of species 占总种数比例 Percentage of total species (%) 鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78 小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39 多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39 红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87 小菇属 Mycena 11 5.26 光柄菇属 Pluteus 5 2.39 红菇属 Russula 17 8.13 栓菌属 Trametes 5 2.39
关闭全屏
BibTeX
EndNote
RefWorks
TxT