欢迎来到天天文库
浏览记录
ID:59191253
大小:12.19 MB
页数:37页
时间:2020-09-26
《秦晓飞系列-深度学习-3.2机器学习策略2(迁移学习)ppt课件.ppt》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、机器学习策略(2)MachineLearningStrategy(2)主讲教师:秦晓飞上海理工大学光电学院2.1CarryingoutErrorAnalysis2.1CarryingoutErrorAnalysisLookatdevexamplestoevaluateideasSupposeyourcatclassifierachieved90%accuracy(10%error),whichisnotverygood.Youlookatthemisrecognizedcatsandfindsomeofthemaredogs.Shouldyoutr
2、ytomakeyourcatclassifierdobetterondogs?Erroranalysis:Get~100mislabeleddevsetexamples.Countuphowmanyaredogs.5%5/100Ceilingimprovement5%Error10%→9.5%50%50/100Ceilingimprovement50%Error10%→5%2.1CarryingoutErrorAnalysisEvaluatemultipleideasinparallelIdeasforcatdetection:Fixpicture
3、sofdogsbeingrecognizedascats.Fixgreatcats(lions,panthers,etc..)beingmisrecognized.Improveperformanceonblurryimages.ImagesDogsGreatcatsBlurComments123100%oftotal√√√√√√PitballRainyday,zoo8%43%61%12%Instagramfilter2.2CleaningupIncorrectlyLabeledData2.2CleaningupIncorrectlyLabeled
4、DataIncorrectlylabeledexamplesDLalgorithmsarequiterobusttorandomerrorsinthetrainingset.xy1011011DLalgorithmscannothandlesystematicerrors,suchasrecognizingallwhitedogsascats.Incorrectlylabeleddataindev/testsetmayhurtDLalgorithms’performance.Youneedtodoerroranalysistodecidewheth
5、ertocorrectthem.2.2CleaningupIncorrectlyLabeledDataErroranalysisImagesDogsGreatcatsBlurComments9899100%oftotal√√√LabelermissedcatinbackgroundDrawingofacat;Notarealcat.8%43%61%6%Incorrectlylabeled30%Overalldevseterror…………………...10%Errorsduetoincorrectlabels……….0.6%Errorsduetooth
6、ercauses…..……….9.4%2%0.6%1.4%GoalofdevsetistohelpyouselectbetweentwoclassifiersA&B.2.1%1.9%2.2CleaningupIncorrectlyLabeledDataGuidelinesofcorrectingincorrectdev/testsetexamplesApplysameprocesstoyourdevandtestsetstomakesuretheycontinuetocomefromthesamedistribution.Considerexami
7、ningexamplesyouralgorithmgotrightaswellasonesitgotwrong.(Howeverthisismoredifficultthanonlydoingitonwrong,becauserightexamplesismuchmorethanwrongexamples.)Trainanddev/testdatamaynowcomefromslightlydifferentdistributions.2.3BuildYourFirstSystemQuickly,thenIterate2.3BuildYourFi
8、rstSystemQuickly,thenIterateWhenbuildingabrandnewMLsystem,the
此文档下载收益归作者所有