2023年全國碩士研究生考試考研英語一試題真題（含答案詳解+作文范文）_第1頁
已閱讀1頁，還剩20頁未讀， 繼續(xù)免費(fèi)閱讀

下載本文檔

版權(quán)說明：本文檔由用戶提供并上傳，收益歸屬內(nèi)容提供方，若內(nèi)容存在侵權(quán)，請進(jìn)行舉報(bào)或認(rèn)領(lǐng)

文檔簡介

1、1MachineLearningResearchFourCurrentDirectionsThomasG.Dietterich■Machinelearningresearchhasbeenmakinggreatprogressinmanydirections.Thisarticlesummarizesfourofthesedirectionsdiscussessomecurrentopenproblems.Thefourdirectio

2、nsare(1)theimprovementofclassificationaccuracybylearningensemblesofclassifiers(2)methodsfscalingupsupervisedlearningalgithms(3)reinfcementlearning(4)thelearningofcomplexstochasticmodels.Thelastfiveyearshaveseenanexplosio

3、ninmachinelearningresearch.Thisexplosionhasmanycauses:Firstseparateresearchcommunitiesinsymbolicmachinelearningcomputationlearningtheyneuralwksstatisticspatternrecognitionhavediscoveredoneanotherbeguntowktogether.Secondm

4、achinelearningtechniquesarebeingappliedtonewkindsofproblemincludingknowledgediscoveryindatabaseslanguageprocessingrobotcontrolcombinatialoptimizationaswellastometraditionalproblemssuchasspeechrecognitionfacerecognitionhw

5、ritingrecognitionmedicaldataanalysisgameplaying.InthisarticleIedfourtopicswithinmachinelearningwheretherehasbeenalotofrecentactivity.ThepurposeofthearticleistodescribetheresultsintheseareastoabroaderAIaudiencetosketchsom

6、eoftheopenresearchproblems.Thetopicareasare(1)ensemblesofclassifiers(2)methodsfscalingupsupervisedlearningalgithms(3)reinfcementlearning(4)thelearningofcomplexstochasticmodels.Thereadershouldbecautionedthatthisarticleisn

7、otacomprehensivereviewofeachofthesetopics.Rathermygoalistoprovidearepresentativesampleoftheresearchineachofthesefourareas.Ineachoftheareastherearemanyotherpapersthatdescriberelevantwk.IapologizetothoseauthswhosewkIwasuna

8、bletoincludeinthearticle.EnsemblesEnsemblesofofClassifiersClassifiersThefirsttopicconcernsmethodsfimprovingaccuracyinsupervisedlearning.Ibeginbyintroducingsomenotation.Insupervisedlearningalearningprogramisgiventraininge

9、xamplesofthefm(x1y1)…(xmym)fsomeunknownfunctiony=f(x).Thexivaluesaretypicallyvectsofthefmwhosecomponentsarediscreterealvaluedsuchasheightweightcolage.ThesearealsocalledthefeatureofXiIusethenotationXijto.refertothejth3hyp

10、otheses.Thelearningalgithmisrunseveraltimeseachtimewithadifferentsubsetofthetrainingexamples.Thistechniquewksespeciallywellfunstablelearningalgithmsalgithmswhoseoutputclassifierundergoesmajchangesinresponsetosmallchanges

11、inthetrainingdata.Decisiontreeneuralwkrulelearningalgithmsareallunstable.Linearregressionnearestneighblinearthresholdalgithmsaregenerallystable.Themoststraightfwardwayofmanipulatingthetrainingsetiscalledbagging.Oneachrun

12、baggingpresentsthelearningalgithmwithatrainingsetthatconsistofasampleofmtrainingexamplesdrawnromlywithreplacementfromtheiginaltrainingsetofmitems.Suchatrainingsetiscalledabootstrapreplicateoftheiginaltrainingsetthetechni

13、queiscalledbootstrapaggregation(Breiman1996a).Eachbootstrapreplicatecontainsontheaverage63.2percentoftheiginalsetwithseveraltrainingexamplesappearingmultipletimes.Anothertrainingsetsamplingmethodistoconstructthetrainings

14、etsbyleavingoutdisjointsubsets.Then10overlappingtrainingsetscanbedividedromlyinto10disjointsubsets.Then10overlappingtrainingsetscanbeconstructedbypingoutadifferentisusedtoconstructtrainingsetsftenfoldcrossvalidationsoens

15、emblesconstructedinthiswayaresometimescalledcrossvalidatedcommittees(ParmantoMunroDoyle1996).ThethirdmethodfmanipulatingthetrainingsetisillustratedbytheADABOOSTalgithmdevelopedbyFreundSchapire(19961995)showninfigure2.Lik

16、ebaggingADABOOSTmanipulatesthetrainingexamplestogeneratemultiplehypotheses.ADABOOSTmaintainsaprobabilitydistributionpi(x)overthetrainingexamples.Ineachiterationiitdrawsatrainingsetofsizembysamplingwithreplacementaccdingt

17、otheprobabilitydistributionpi(x).Thelearningalgithmisthenappliedtoproduceaclassifierhi.Theerrrate￡iofthisclassifieronthetrainingexamples(weightedaccdingtopi(x))iscomputedusedtoadjusttheprobabilitydistributiononthetrainin

18、gexamples.(Infigure2notethattheprobabilitydistributionisobtainedbynmalizingasetofweightswi(i)overthetrainingexamples.)Theeffectofthechangeinweightsistoplacemeweightonexamplesthatweremisclassifiedbyhilessweightonexamplest

19、hatwerecrectlyclassified.InsubsequentiterationstherefeADABOOSTconstructsprogressivelymedifficultlearningproblems.Thefinalclassifierhiisconstructsbyaweightedvoteoftheindividualclassifiers.Eachclassifierisweightedaccdingto

溫馨提示

  • 1. 本站所有資源如無特殊說明，都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
  • 2. 本站的文檔不包含任何第三方提供的附件圖紙等，如果需要附件，請聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
  • 3. 本站RAR壓縮包中若帶圖紙，網(wǎng)頁內(nèi)容里面會有圖紙預(yù)覽，若沒有圖紙預(yù)覽就沒有圖紙。
  • 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
  • 5. 眾賞文庫僅提供信息存儲空間，僅對用戶上傳內(nèi)容的表現(xiàn)方式做保護(hù)處理，對用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯，并不能對任何下載內(nèi)容負(fù)責(zé)。
  • 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容，請與我們聯(lián)系，我們立即糾正。
  • 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時也不承擔(dān)用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。

評論

0/150

提交評論