[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

ID：40702386

大?。?.33 MB

頁數(shù)：8頁

時間：2019-08-06

[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations_第1頁
[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations_第2頁
[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations_第3頁
[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations_第4頁
[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations_第5頁
資源描述：

《[ICML 2009 Honglak, Andrew] Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations》由會員上傳分享，免費在線閱讀，更多相關內(nèi)容在學術論文-天天文庫。

1、ConvolutionalDeepBeliefNetworksforScalableUnsupervisedLearningofHierarchicalRepresentationsHonglakLeehllee@cs.stanford.eduRogerGrossergrosse@cs.stanford.eduRajeshRanganathrajeshr@cs.stanford.eduAndrewY.Ngang@cs.stanford.eduComputerScienceDepartment,StanfordUnive

2、rsity,Stanford,CA94305,USAAbstractlower-levelambiguitiesintheimageorinfertheloca-Therehasbeenmuchinterestinunsuper-tionsofhiddenobjectparts.visedlearningofhierarchicalgenerativemod-Deeparchitecturesconsistoffeaturedetectorunitsar-elssuchasdeepbeliefnetworks.Scal

3、ingrangedinlayers.Lowerlayersdetectsimplefeaturessuchmodelstofull-sized,high-dimensionalandfeedintohigherlayers,whichinturndetectmoreimagesremainsadicultproblem.Toad-complexfeatures.Therehavebeenseveralapproachesdressthisproblem,wepresenttheconvolu-tolearningde

4、epnetworks(LeCunetal.,1989;Bengiotionaldeepbeliefnetwork,ahierarchicalgen-etal.,2006;Ranzatoetal.,2006;Hintonetal.,2006).erativemodelwhichscalestorealisticimageInparticular,thedeepbeliefnetwork(DBN)(Hintonsizes.Thismodelistranslation-invariantandetal.,2006)isamu

5、ltilayergenerativemodelwheresupportsecientbottom-upandtop-downeachlayerencodesstatisticaldependenciesamongtheprobabilisticinference.Keytoourapproachunitsinthelayerbelowit;itistrainedto(approxi-isprobabilisticmax-pooling,anoveltechniquemately)maximizethelikeliho

6、odofitstrainingdata.whichshrinkstherepresentationsofhigherDBNshavebeensuccessfullyusedtolearnhigh-levellayersinaprobabilisticallysoundway.Ourstructureinawidevarietyofdomains,includinghand-experimentsshowthatthealgorithmlearnswrittendigits(Hintonetal.,2006)andhum

7、anmotionusefulhigh-levelvisualfeatures,suchasob-capturedata(Tayloretal.,2007).Webuilduponthejectparts,fromunlabeledimagesofobjectsDBNinthispaperbecauseweareinterestedinlearn-andnaturalscenes.Wedemonstrateexcel-ingagenerativemodelofimageswhichcanbetrainedlentperf

8、ormanceonseveralvisualrecogni-inapurelyunsupervisedmanner.tiontasksandshowthatourmodelcanper-formhierarchical(bottom-upandtop-down)WhileDBNshavebeensuccessfulincontro

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(shù)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(quán)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(quán)有爭議請及時聯(lián)系客服。
3. 下載前請仔細閱讀文檔內(nèi)容，確認文檔內(nèi)容符合您的需求后進行下載，若出現(xiàn)內(nèi)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(wǎng)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。