计算机专业文献翻译-机器学习的研究.doc

计算机专业文献翻译-机器学习的研究.doc

ID:61336766

大小:131.50 KB

页数:22页

时间:2021-01-25

计算机专业文献翻译-机器学习的研究.doc_第1页
计算机专业文献翻译-机器学习的研究.doc_第2页
计算机专业文献翻译-机器学习的研究.doc_第3页
计算机专业文献翻译-机器学习的研究.doc_第4页
计算机专业文献翻译-机器学习的研究.doc_第5页
资源描述:

《计算机专业文献翻译-机器学习的研究.doc》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、Machine-LearningResearchFourCurrentDirectionsThomasG.Dietterich■Machine-learningresearchhasbeenmakinggreatprogressinmanydirections.Thisarticlesummarizesfourofthesedirectionsanddiscussessomecurrentopenproblems.Thefourdirectionsare(1)theimprovementofclassificationaccuracybylearningensemblesofcl

2、assifiers,(2)methodsforscalingupsupervisedlearningalgorithms,(3)reinforcementlearning,and(4)thelearningofcomplexstochasticmodels.Thelastfiveyearshaveseenanexplosioninmachine-learningresearch.Thisexplosionhasmanycauses:First,separateresearchcommunitiesinsymbolicmachinelearning,computationlearn

3、ingtheory,neuralnetworks,statistics,andpatternrecognitionhavediscoveredoneanotherandbeguntoworktogether.Second,machine-learningtechniquesarebeingappliedtonewkindsofproblem,includingknowledgediscoveryindatabases,languageprocessing,robotcontrol,andcombinatorialoptimization,aswellastomoretraditi

4、onalproblemssuchasspeechrecognition,facerecognition,handwritingrecognition,medicaldataanalysis,andgameplaying.Inthisarticle,Iselectedfourtopicswithinmachinelearningwheretherehasbeenalotofrecentactivity.ThepurposeofthearticleistodescribetheresultsintheseareastoabroaderAIaudienceandtosketchsome

5、oftheopenresearchproblems.Thetopicareasare(1)ensemblesofclassifiers,(2)methodsforscalingupsupervisedlearningalgorithms,(3)reinforcementlearning,and(4)thelearningofcomplexstochasticmodels.Thereadershouldbecautionedthatthisarticleisnotacomprehensivereviewofeachofthesetopics.Rather,mygoalistopro

6、videarepresentativesampleoftheresearchineachofthesefourareas.Ineachoftheareas,therearemanyotherpapersthatdescriberelevantwork.IapologizetothoseauthorswhoseworkIwasunabletoincludeinthearticle.EnsemblesofClassifiersThefirsttopicconcernsmethodsforimprovingaccuracyinsupervisedlearning.Ibeginbyint

7、roducingsomenotation.Insupervisedlearning,alearningprogramisgiventrainingexamplesoftheform{(x1,y1),…,(xm,ym)}forsomeunknownfunctiony=f(x).Thexivaluesaretypicallyvectorsoftheformwhosecomponentsarediscreteorrealvalued,suchash

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。