[dataguru.cn]Understanding Deep Convolutional Networks

[dataguru.cn]Understanding Deep Convolutional Networks

ID：40702290

大?。?.46 MB

頁數：17頁

時間：2019-08-06

[dataguru.cn]Understanding Deep Convolutional Networks_第1頁
[dataguru.cn]Understanding Deep Convolutional Networks_第2頁
[dataguru.cn]Understanding Deep Convolutional Networks_第3頁
[dataguru.cn]Understanding Deep Convolutional Networks_第4頁
[dataguru.cn]Understanding Deep Convolutional Networks_第5頁
資源描述：

《[dataguru.cn]Understanding Deep Convolutional Networks》由會員上傳分享，免費在線閱讀，更多相關內容在學術論文-天天文庫。

1、UnderstandingDeepConvolutionalNetworksStephaneMallatEcoleNormaleSuperieure,CNRS,PSL45rued'Ulm,75005Paris,FranceToappearinPhilosophicalTransactionsAin2016AbstractDeepconvolutionalnetworksprovidestateoftheartclassi cationsandregressionsresultsovermanyhigh-dimensional

2、problems.Wereviewtheirarchitecture,whichscattersdatawithacascadeoflinear lterweightsandnon-linearities.Amathematicalframeworkisintroducedtoanalyzetheirproperties.Computationsofinvariantsinvolvemultiscalecontractions,thelinearizationofhierarchicalsymmetries,andsparsese

3、parations.Applicationsarediscussed.x1IntroductionSupervisedlearningisahigh-dimensionalinterpolationproblem.Weapproximateafunctionf(x)fromqtrainingsamplesfxi;f(xi)g,wherexisadatavectorofveryhighdimensiond.Thisdimensionisofteniqlargerthan106,forimagesorotherlargesizesi

4、gnals.Deepconvolutionalneuralnetworkshaverecentlyobtainedremarkableexperimentalresults[21].Theygivestateoftheartperformancesforimageclassi cationwiththousandsofcomplexclasses[19],speechrecognition[17],bio-medicalapplications[22],naturallanguageunderstanding[30],andinm

5、anyotherdomains.Theyarealsostudiedasneuro-physiologicalmodelsofvision[4].Multilayerneuralnetworksarecomputationallearningarchitectureswhichpropagatetheinputdataacrossasequenceoflinearoperatorsandsimplenon-linearities.Thepropertiesofshallownetworks,withonehiddenlayer,a

6、rewellunderstoodasdecompositionsinfamiliesofridgefunctions[10].However,theseapproachesdonotextendtonetworkswithmorelayers.Deepconvolutionalneuralnetworks,introducedbyarXiv:1601.04920v1[stat.ML]19Jan2016LeCun[20],areimplementedwithlinearconvolutionsfollowedbynon-linear

7、ities,overtypicallymorethan5layers.Thesecomplexprogrammablemachines,de nedbypotentiallybillionsof lterweights,bringustoadi erentmathematicalworld.Manyresearchershavepointedoutthatdeepconvolutionnetworksarecomputingprogressivelymorepowerfulinvariantsasdepthincreases[4,

8、21],butrelationswithnetworksweightsandnon-linearitiesarecomplex.Thispaperaimsatclarifyingimportantprincipleswhichgovernthepr

當前文檔最多預覽五頁，下載文檔查看全文

此文檔下載收益歸作者所有

當前文檔最多預覽五頁，下載文檔查看全文
溫馨提示：
1. 部分包含數學公式或PPT動畫的文件，查看預覽時可能會顯示錯亂或異常，文件下載后無此問題，請放心下載。
2. 本文檔由用戶上傳，版權歸屬用戶，天天文庫負責整理代發(fā)布。如果您對本文檔版權有爭議請及時聯(lián)系客服。
3. 下載前請仔細閱讀文檔內容，確認文檔內容符合您的需求后進行下載，若出現內容與標題不符可向本站投訴處理。
4. 下載文檔時可能由于網絡波動等原因無法下載或下載錯誤，付費完成后未能成功下載的用戶請聯(lián)系客服處理。