course20 Deep Learning for Coders, 2020, the websi

我要开发同款
匿名用户2021年11月11日
56阅读
开发技术Python
所属分类人工智能、机器学习/深度学习
授权协议Apache-2.0 License

作品详情

PracticalDeepLearningforCoders

DeepLearningforCoderswithfastaiandPyTorch:AIApplicationsWithoutaPhD-thebookandthecourse

WelcometoPracticalDeepLearningforCoders.Thiswebsitecoversthebookandthe2020versionofthecourse,whicharedesignedtoworkcloselytogether.Ifyouhaven'tyetgotthebook,youcanbuyithere.It'salsofreelyavailableasinteractiveJupyterNotebooks;readontolearnhowtoaccessthem..

HowdoIgetstarted?

Ifyou'rereadytodiveinrightnow,here'showtogetstarted.Ifyouwanttoknowmoreaboutthiscourse,readthenextsections,andthencomebackhere.

Towatchthevideos,clickontheLessonssectioninthenavigationsidebar.Thelessonsallhavesearchabletranscripts;click"TranscriptSearch"inthetoprightpaneltosearchforawordorphrase,andthenclickittojumpstraighttovideoatthetimethatappearsinthetranscript.ThevideosareallcaptionedandalsotranslatedintoChinese(简体中文)andSpanish;whilewatchingthevideoclickthe"CC"buttontoturnthemonandoff,andthesettingbuttontochangethelanguage.

Eachvideocoversachapterfromthebook.TheentiretyofeverychapterofthebookisavailableasaninteractiveJupyterNotebook.JupyterNotebookisthemostpopulartoolfordoingdatascienceinPython,forgoodreason.Itispowerful,flexible,andeasytouse.Wethinkyouwillloveit!Sincethemostimportantthingforlearningdeeplearningiswritingcodeandexperimenting,it'simportantthatyouhaveagreatplatformforexperimentingwithcode.

Togetstarted,werecommendusingaJupyterServerfromoneoftherecommendedonlineplatforms(clickthelinksforinstructionsonhowtousetheseforthecourse):

Colab:ApopularfreeservicefromGoogle.Googlehavechangedthenotebookplatformquitealot,sokeyboardshortcutsaredifferent,andnoteverythingworks(e.g.muchofchapter2doesn'tworkbecauseColabdoesn'tsupportcreatingwebappGUIs)Gradient:UnlikeColab,thisisa"real"JupyterNotebooksoeverythinginthecourseworks.Italsoprovidesspacetosaveyournotebooksandmodels.However,sometimesthefreeserversgetover-loaded,andwhenthathappensit'simpossibletoconnect.

IfyouareinterestedintheexperienceofrunningafullLinuxserver,youcanconsiderDataCrunch.io(verynewservicesowedon'tknowhowgooditis,nosetuprequired,extremelygoodvalueandextremelyfastGPUs),orGoogleCloud(extremelypopularservice,veryreliable,butthefastestGPUsarefarmoreexpensive).Westronglysuggestusingoneoftherecommendedonlineplatformsforrunningthenotebooks,andtonotuseyourowncomputer,unlessyou'reveryexperiencedwithLinuxsystemadminstrationandhandlingGPUdrivers,CUDA,andsoforth.

Ifyouneedhelp,there'sawonderfulonlinecommunityreadytohelpyouatforums.fast.ai.Beforeaskingaquestionontheforums,searchcarefullytoseeifyourquestionhasbeenansweredbefore.(Theforumsystemwon'tletyoupostuntilyou'vespentafewminutesonthesitereadingexistingtopics.)OnebitthatmanystudentsfindtrickyisgettingsignedupfortheBingAPIfortheimagedownloadtaskinlesson2;here'sahelpfulforumpostexplaininghowtogettheBingAPIkeyyou'llneedfordownloadingimages.

Isthiscourseforme?

Thankyouforlettingusjoinyouonyourdeeplearningjourney,howeverfaralongthatyoumaybe!Previousfast.aicourseshavebeenstudiedbyhundredsofthousandsofstudents,fromallwalksoflife,fromallpartsoftheworld.Manystudentshavetoldusabouthowthey'vebecomemultiplegoldmedalwinnersofinternationalmachinelearningcompetitions,receivedoffersfromtopcompanies,andhavingresearchpaperspublished.Forinstance,IsaacDimitrovskytoldusthathehad"beenplayingaroundwithMLforacoupleofyearswithoutreallygrokkingit...[then]wentthroughthefast.aipart1courselatelastyear,anditclickedforme".HewentontoachievefirstplaceintheprestigiousinternationalRA2-DREAMChallengecompetition!Hedevelopedamultistagedeeplearningmethodforscoringradiographichandandfootjointdamageinrheumatoidarthritis,takingadvantageofthefastailibrary.

Itdoesn'tmatterifyoudon'tcomefromatechnicaloramathematicalbackground(thoughit'sokayifyoudotoo!);wewrotethiscoursetomakedeeplearningaccessibletoasmanypeopleaspossible.Theonlyprerequisiteisthatyouknowhowtocode(ayearofexperienceisenough),preferablyinPython,andthatyouhaveatleastfollowedahighschoolmathcourse.Thefirstthreechaptershavebeenexplicitlywritteninawaythatwillallowexecutives,productmanagers,etc.tounderstandthemostimportantthingsthey'llneedtoknowaboutdeeplearning--ifthat'syou,justskipoverthecodeinthosesections.

Deeplearningisacomputertechniquetoextractandtransformdata–-withusecasesrangingfromhumanspeechrecognitiontoanimalimageryclassification–-byusingmultiplelayersofneuralnetworks.Alotofpeopleassumethatyouneedallkindsofhard-to-findstufftogetgreatresultswithdeeplearning,butasyou'llseeinthiscourse,thosepeoplearewrong.Here'safewthingsyouabsolutelydon'tneedtodoworld-classdeeplearning:

Myth(don'tneed)TruthLotsofmathJusthighschoolmathissufficientLotsofdataWe'veseenrecord-breakingresultswith<50itemsofdataLotsofexpensivecomputersYoucangetwhatyouneedforstateoftheartworkforfree

Deeplearninghaspower,flexibility,andsimplicity.That'swhywebelieveitshouldbeappliedacrossmanydisciplines.Theseincludethesocialandphysicalsciences,thearts,medicine,finance,scientificresearch,andmanymore.Here'salistofsomeofthethousandsoftasksindifferentareasatwhichdeeplearning,ormethodsheavilyusingdeeplearning,isnowthebestintheworld:

Naturallanguageprocessing(NLP)Answeringquestions;speechrecognition;summarizingdocuments;classifyingdocuments;findingnames,dates,etc.indocuments;searchingforarticlesmentioningaconceptComputervisionSatelliteanddroneimageryinterpretation(e.g.,fordisasterresilience);facerecognition;imagecaptioning;readingtrafficsigns;locatingpedestriansandvehiclesinautonomousvehiclesMedicineFindinganomaliesinradiologyimages,includingCT,MRI,andX-rayimages;countingfeaturesinpathologyslides;measuringfeaturesinultrasounds;diagnosingdiabeticretinopathyBiologyFoldingproteins;classifyingproteins;manygenomicstasks,suchastumor-normalsequencingandclassifyingclinicallyactionablegeneticmutations;cellclassification;analyzingprotein/proteininteractionsImagegenerationColorizingimages;increasingimageresolution;removingnoisefromimages;convertingimagestoartinthestyleoffamousartistsRecommendationsystemsWebsearch;productrecommendations;homepagelayoutPlayinggamesChess,Go,mostAtarivideogames,andmanyreal-timestrategygamesRoboticsHandlingobjectsthatarechallengingtolocate(e.g.,transparent,shiny,lackingtexture)orhardtopickupOtherapplicationsFinancialandlogisticalforecasting,texttospeech,andmuchmore...Whoweare

WeareSylvainGuggerandJeremyHoward,yourguidesonthisjourney.We'retheco-authorsoffastai,thesoftwarethatyou'llbeusingthroughoutthiscourse.

Jeremyhasbeenusingandteachingmachinelearningforaround30years.Hestartedusingneuralnetworks25yearsago.Duringthistime,hehasledmanycompaniesandprojectsthathavemachinelearningattheircore,includingfoundingthefirstcompanytofocusondeeplearningandmedicine,Enlitic,andtakingontheroleofPresidentandChiefScientistoftheworld'slargestmachinelearningcommunity,Kaggle.Heistheco-founder,alongwithDr.RachelThomas,offast.ai,theorganizationthatbuiltthecoursethiscourseisbasedon.

Sylvainhaswritten10mathtextbooks,coveringtheentireadvancedFrenchmathscurriculum!HeisnowaresearcheratHuggingFace,andwaspreviouslyaresearcheratfast.ai.

Wecarealotaboutteaching.Inthiscourse,westartbyshowinghowtouseacomplete,working,veryusable,state-of-the-artdeeplearningnetworktosolvereal-worldproblems,usingsimple,expressivetools.Andthenwegraduallydigdeeperanddeeperintounderstandinghowthosetoolsaremade,andhowthetoolsthatmakethosetoolsaremade,andsoon…Wealwaysteachingthroughexamples.Weensurethatthereisacontextandapurposethatyoucanunderstandintuitively,ratherthanstartingwithalgebraicsymbolmanipulation.

Thesoftwareyouwillbeusing

Inthiscourse,you'llbeusingPyTorchandfastai.

We'vecompletedhundredsofmachinelearningprojectsusingdozensofdifferentpackages,andmanydifferentprogramminglanguages.Atfast.ai,wehavewrittencoursesusingmostofthemaindeeplearningandmachinelearningpackagesusedtoday.WespentoverathousandhourstestingPyTorchbeforedecidingthatwewoulduseitforfuturecourses,softwaredevelopment,andresearch.PyTorchisnowtheworld'sfastest-growingdeeplearninglibraryandisalreadyusedformostresearchpapersattopconferences.

PyTorchworksbestasalow-levelfoundationlibrary,providingthebasicoperationsforhigher-levelfunctionality.Thefastailibraryisthemostpopularlibraryforaddingthishigher-levelfunctionalityontopofPyTorch.Inthiscourse,aswegodeeperanddeeperintothefoundationsofdeeplearning,wewillalsogodeeperanddeeperintothelayersoffastai.Thiscoursecoversversion2ofthefastailibrary,whichisafrom-scratchrewriteprovidingmanyuniquefeatures.

Whatyouwilllearn

Afterfinishingthiscourseyouwillknow:

Howtotrainmodelsthatachievestate-of-the-artresultsin:Computervision,includingimageclassification(e.g., classifyingpetphotosbybreed),andimagelocalizationanddetection(e.g., findingwheretheanimalsinanimageare)Naturallanguageprocessing(NLP),includingdocumentclassification(e.g., moviereviewsentimentanalysis)andlanguagemodelingTabulardata(e.g., salesprediction)withcategoricaldata,continuousdata,andmixeddata,includingtimeseriesCollaborativefiltering(e.g., movierecommendation)Howtoturnyourmodelsintowebapplications,anddeploythemWhyandhowdeeplearningmodelswork,andhowtousethatknowledgetoimprovetheaccuracy,speed,andreliabilityofyourmodelsThelatestdeeplearningtechniquesthatreallymatterinpracticeHowtoimplementstochasticgradientdescentandacompletetrainingloopfromscratchHowtothinkabouttheethicalimplicationsofyourwork,tohelpensurethatyou'remakingtheworldabetterplaceandthatyourworkisn'tmisusedforharm

Herearesomeofthetechniquescovered(don'tworryifnoneofthesewordsmeananythingtoyouyet--you'lllearnthemallsoon):

RandomforestsandgradientboostingAffinefunctionsandnonlinearitiesParametersandactivationsRandominitializationandtransferlearningSGD,Momentum,Adam,andotheroptimizersConvolutionsBatchnormalizationDropoutDataaugmentationWeightdecayImageclassificationandregressionEntityandwordembeddingsRecurrentneuralnetworks(RNNs)SegmentationAndmuchmore
声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论