




已阅读5页,还剩26页未读, 继续免费阅读
版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
WARNING:OPTIONALEXTRAMATERIAL,Thematerialinthisvideoisconsiderablymoredifficultthaninmostoftheothervideos.IhaveincludeditforthosewhowanttogetsomeideaofhowtheHFoptimizerworks.YoudonotneedtounderstandhowHFworksinordertounderstandtheremainingvideosinlecture8.Thequestionsintheweeklyquizandthefinaltestwillnotbeaboutthematerialinthisvideo,soyoucansafelyskipitifyouwant.,NeuralNetworksforMachineLearningLecture8aAbriefoverviewof“Hessian-Free”optimization,Howmuchcanwereducetheerrorbymovinginagivendirection?,Ifwechooseadirectiontomoveinandwekeepgoinginthatdirection,howmuchdoestheerrordecreasebeforeitstartsrisingagain?Weassumethecurvatureisconstant(i.e.itsaquadraticerrorsurface).Assumethemagnitudeofthegradientdecreasesaswemovedownthegradient(i.e.theerrorsurfaceisconvexupward).Themaximumerrorreductiondependsontheratioofthegradienttothecurvature.Soagooddirectiontomoveinisonewithahighratioofgradienttocurvature,evenifthegradientitselfissmall.Howcanwefinddirectionslikethese?,betterratio,Newtonsmethod,Thebasicproblemwithsteepestdescentonaquadraticerrorsurfaceisthatthegradientisnotthedirectionwewanttogoin.Iftheerrorsurfacehascircularcross-sections,thegradientisfine.Soletsapplyalineartransformationthatturnsellipsesintocircles.Newtonsmethodmultipliesthegradientvectorbytheinverseofthecurvaturematrix,H:Onarealquadraticsurfaceitjumpstotheminimuminonestep.Unfortunately,withonlyamillionweights,thecurvaturematrixhasatrilliontermsanditistotallyinfeasibletoinvertit.,CurvatureMatrices,Eachelementinthecurvaturematrixspecifieshowthegradientinonedirectionchangesaswemoveinsomeotherdirection.Theoff-diagonaltermscorrespondtotwistsintheerrorsurface.Thereasonsteepestdescentgoeswrongisthatthegradientforoneweightgetsmessedupbythesimultaneouschangestoalltheotherweights.Thecurvaturematrixdeterminesthesizesoftheseinteractions.,ijk,ijk,Howtoavoidinvertingahugematrix,Thecurvaturematrixhastoomanytermstobeofuseinabignetwork.Maybewecangetsomebenefitfromjustusingthetermsalongtheleadingdiagonal(LeCun).Butthediagonaltermsareonlyatinyfractionoftheinteractions(theyaretheself-interactions).ThecurvaturematrixcanbeapproximatedinmanydifferentwaysHessian-freemethods,LBFGS,IntheHFmethod,wemakeanapproximationtothecurvaturematrixandthen,assumingthatapproximationiscorrect,weminimizetheerrorusinganefficienttechniquecalledconjugategradient.Thenwemakeanotherapproximationtothecurvaturematrixandminimizeagain.ForRNNsitsimportanttoaddapenaltyforchanginganyofthehiddenactivitiestoomuch.,Conjugategradient,Thereisanalternativetogoingtotheminimuminonestepbymultiplyingbytheinverseofthecurvaturematrix.Useasequenceofstepseachofwhichfindstheminimumalongonedirection.Makesurethateachnewdirectionis“conjugate”tothepreviousdirectionssoyoudonotmessuptheminimizationyoualreadydid.“conjugate”meansthatasyougointhenewdirection,youdonotchangethegradientsinthepreviousdirections.,Apictureofconjugategradient,Thegradientinthedirectionofthefirststepiszeroatallpointsonthegreenline.Soifwemovealongthegreenlinewedontmessuptheminimizationwealreadydidinthefirstdirection.,Whatdoesconjugategradientachieve?,AfterNsteps,conjugategradientisguaranteedtofindtheminimumofanN-dimensionalquadraticsurface.Why?AftermanylessthanNstepsithastypicallygottheerrorveryclosetotheminimumvalue.Conjugategradientcanbeapplieddirectlytoanon-quadraticerrorsurfaceanditusuallyworksquitewell(non-linearconjugategrad.)TheHFoptimizerusesconjugategradientforminimizationonagenuinelyquadraticsurfacewhereitexcels.Thegenuinelyquadraticsurfaceisthequadraticapproximationtothetruesurface.,NeuralNetworksforMachineLearningLecture8bModelingcharacterstringswithmultiplicativeconnections,Modelingtext:Advantagesofworkingwithcharacters,Thewebiscomposedofcharacterstrings.Anylearningmethodpowerfulenoughtounderstandtheworldbyreadingtheweboughttofindittrivialtolearnwhichstringsmakewords(thisturnsouttobetrue,asweshallsee).Pre-processingtexttogetwordsisabighassleWhataboutmorphemes(prefixes,suffixesetc)Whataboutsubtleeffectslike“sn”words?WhataboutNewYork?WhataboutFinnishymmartamattomyydellansakaan,.,.,.,.,.,.,.,.,Anobviousrecurrentneuralnet,1500hiddenunits,character:1-of-86,1500hiddenunits,c,predicteddistributionfornextcharacter.,Itsaloteasiertopredict86charactersthan100,000words.,softmax,Asub-treeinthetreeofallcharacterstrings,IfthenodesareimplementedashiddenstatesinanRNN,differentnodescansharestructurebecausetheyusedistributedrepresentations.Thenexthiddenrepresentationneedstodependontheconjunctionofthecurrentcharacterandthecurrenthiddenrepresentation.,.fix,fixi,fixin,i,e,n,InanRNN,eachnodeisahiddenstatevector.Thenextcharactermusttransformthistoanewnode.,fixe,ThereareexponentiallymanynodesinthetreeofallcharacterstringsoflengthN.,Multiplicativeconnections,Insteadofusingtheinputstotherecurrentnettoprovideadditiveextrainputtothehiddenunits,wecouldusethecurrentinputcharactertochoosethewholehidden-to-hiddenweightmatrix.Butthisrequires86x1500 x1500parametersThiscouldmakethenetoverfit.Canweachievethesamekindofmultiplicativeinteractionusingfewerparameters?Wewantadifferenttransitionmatrixforeachofthe86characters,butwewantthese86character-specificweightmatricestoshareparameters(thecharacters9and8shouldhavesimilarmatrices).,Usingfactorstoimplementmultiplicativeinteractions,Wecangetgroupsaandbtointeractmultiplicativelybyusing“factors”.Eachfactorfirstcomputesaweightedsumforeachofitsinputgroups.Thenitsendstheproductoftheweightedsumstoitsoutputgroup.,vectorofinputstogroupc,scalarinputtoffromgroupb,scalarinputtoffromgroupa,Groupb,Groupa,Groupc,Usingfactorstoimplementasetofbasismatrices,Wecanthinkaboutfactorsanotherway:Eachfactordefinesarank1transitionmatrixfromatoc.,scalarcoefficient,outerproducttransitionmatrixwithrank1,Groupb,Groupa,Groupc,1500hiddenunits,character:1-of-86,Using3-wayfactorstoallowacharactertocreateawholetransitionmatrix,predicteddistributionfornextcharacter,1500hiddenunits,Eachfactor,f,definesarankonematrix,Eachcharacter,k,determinesagainforeachofthesematrices.,k,NeuralNetworksforMachineLearningLecture8cLearningtopredictthenextcharacterusingHF,Trainingthecharactermodel,IlyaSutskeverused5millionstringsof100characterstakenfromwikipedia.Foreachstringhestartspredictingatthe11thcharacter.UsingtheHFoptimizer,ittookamonthonaGPUboardtogetareallygoodmodel.IlyascurrentbestRNNisprobablythebestsinglemodelforcharacterprediction(combinationsofmanymodelsdobetter).Itworksinaverydifferentwayfromthebestothermodels.Itcanbalancequotesandbracketsoverlongdistances.Modelsthatrelyonmatchingpreviouscontextscannotdothis.,Howtogeneratecharacterstringsfromthemodel,Startthemodelwithitsdefaulthiddenstate.Giveita“burn-in”sequenceofcharactersandletitupdateitshiddenstateaftereachcharacter.Thenlookattheprobabilitydistributionitpredictsforthenextcharacter.Pickacharacterrandomlyfromthatdistributionandtellthenetthatthiswasthecharacterthatactuallyoccurred.i.e.tellitthatitsguesswascorrect,whateveritguessed.Continuetoletitpickcharactersuntilbored.Lookatthecharacterstringsitproducestoseewhatit“knows”.,HewaselectedPresidentduringtheRevolutionaryWarandforgaveOpusPaulatRome.TheregimeofhiscrewofEngland,isnowArabwomensiconsinandthedemonsthatusesomethingbetweenthecharacterssistersinlowercoiltrainswerealwaysoperatedonthelineoftheephemerablestreet,respectively,thegraphicorotherfacilityfordeformationofagivenproportionoflargesegmentsatRTUS).TheBeverychordwasastronglycoldinternalpalettepoureventhewhiteblade.”,Somecompletionsproducedbythemodel,Sheilathrunges(mostfrequent)Peoplethrunge(mostfrequentnextcharacterisspace)Shiela,ThrungelinidelRey(firsttry)Themeaningoflifeisliteraryrecognition.(6thtry)Themeaningoflifeisthetraditionoftheancienthumanreproduction:itislessfavorabletothegoodboyforwhentoremoveherbigger.(oneofthefirst10triesforamodeltrainedforlonger).,Whatdoesitknow?,Itknowsahugenumberofwordsandalotaboutpropernames,dates,andnumbers.Itisgoodatbalancingquotesandbrackets.Itcancountbrackets:none,one,manyItknowsalotaboutsyntaxbutitsveryhardtopindownexactlywhatformthisknowledgehas.Itssyntacticknowledgeisnotmodular.ItknowsalotofweaksemanticassociationsE.g.itknowsPlatoisassociatedwithWittgensteinandcabbageisassociatedwithvegetable.,RNNsforpredictingthenextword,TomasMikolovandhiscollaboratorshaverecentlytrainedquitelargeRNNsonquitelargetrainingsetsusingBPTT.Theydobetterthanfeed-forwardneuralnets.Theydobetterthanthebestothermodels.Theydoevenbetterwhenaveragedwithothermodels.RNNsrequiremuchlesstrainingdatatoreachthesamelevelofperformanceasothermodels.RNNsimprovefasterthanothermethodsasthedatasetgetsbigger.Thisisgoingtomakethemveryhardtobeat.,NeuralNetworksforMachineLearningLecture8dEchostatenetworks,Thekeyideaofechostatenetworks(perceptronsagain?),Averysimplewaytolearnafeedforwardnetworkistomaketheearlylayersrandomandfixed.Thenwejustlearnthelastlayerwhichisalinearmodelthatusesthetransformedinputstopredictthetargetoutputs.Abigrandomexpansionoftheinputvectorcanhelp.,TheequivalentideaforRNNsistofixtheinputhiddenconnectionsandthehiddenhiddenconnectionsatrandomvaluesandonlylearnthehiddenoutputconnections.Thelearningisthenverysimple(assuminglinearoutputunits).ItsimportanttosettherandomconnectionsverycarefullysotheRNNdoesnotexplodeordie.,SettingtherandomconnectionsinanEchoStateNetwork,Setthehiddenhiddenweightssothatthelengthoftheactivityvectorstaysaboutthesameaftereachiteration.Thisallowstheinputtoechoaroundthenetworkforalongtime.Usesparseconnectivity(i.e.setmostoftheweightstozero).Thiscreateslotsoflooselycoupledoscillators.,Choosethescaleoftheinputhiddenconnectionsverycarefully.Theyneedtodrivethelooselycoupledoscilla
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 国际级自行车比赛电子计时系统租赁与售后保障契约
- 数字科技企业数据总监信息安全责任合同
- 生物药品冷链运输全程温控合作协议
- 商业地产租赁补充合同(含物业管理)
- 母婴行业年度大促联合营销推广合同
- 离婚协议财产分割及变更执行监督协议(含房产)
- 《中国动脉硬化杂志》投稿须知(官方认证)
- DBJ50-T-511-2025 城镇排水系统评价标准
- 国培师德修养学习心得体会模版
- 2023年人教版四年级语文上册五单元测试卷及答案
- 丘市天资报废汽车回收拆解无害化处理项目环境影响报告
- 铸件厂仓库管理制度
- 会阴Ⅲ度Ⅳ度裂伤与缝合课件
- 部编2023版道德与法治六年级下册活动园问题及答案
- 商务数据分析与应用PPT完整版全套教学课件
- 混凝土销售合同电子版(三篇)
- 北京林业大学毕业答辩PPT模板
- 十二指肠解剖
- 第十一章多孔材料课件
- 初中语文人教八年级上册《作文训练之细节描写》PPT
- 高校电子课件:产业经济学(第五版)
评论
0/150
提交评论