返回
2012-ImageNet Classification with Deep Convolutional Neural Networks

2012-ImageNet Classification with Deep Convolutional Neural Networks

ID：40254455

大小：1.35 MB

页数：9页

时间：2019-07-29

2012-ImageNet Classification with Deep Convolutional Neural Networks_第1页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第2页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第3页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第4页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第5页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第6页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第7页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第8页
2012-ImageNet Classification with Deep Convolutional Neural Networks_第9页
资源描述：

《2012-ImageNet Classification with Deep Convolutional Neural Networks》由会员上传分享，免费在线阅读，更多相关内容在学术论文-天天文库。

1、ImageNetClassificationwithDeepConvolutionalNeuralNetworksAlexKrizhevskyIlyaSutskeverGeoffreyE.HintonUniversityofTorontoUniversityofTorontoUniversityofTorontokriz@cs.utoronto.cailya@cs.utoronto.cahinton@cs.utoronto.caAbstractWetrainedalarge,deepconvolutionalneuralnetworktocla

2、ssifythe1.2millionhigh-resolutionimagesintheImageNetLSVRC-2010contestintothe1000dif-ferentclasses.Onthetestdata,weachievedtop-1andtop-5errorratesof37.5%and17.0%whichisconsiderablybetterthanthepreviousstate-of-the-art.Theneuralnetwork,whichhas60millionparametersand650,000neu

3、rons,consistsoffiveconvolutionallayers,someofwhicharefollowedbymax-poolinglayers,andthreefully-connectedlayerswithafinal1000-waysoftmax.Tomaketrain-ingfaster,weusednon-saturatingneuronsandaveryefficientGPUimplemen-tationoftheconvolutionoperation.Toreduceoverfittinginthefully-co

4、nnectedlayersweemployedarecently-developedregularizationmethodcalled“dropout”thatprovedtobeveryeffective.WealsoenteredavariantofthismodelintheILSVRC-2012competitionandachievedawinningtop-5testerrorrateof15.3%,comparedto26.2%achievedbythesecond-bestentry.1IntroductionCurrent

5、approachestoobjectrecognitionmakeessentialuseofmachinelearningmethods.Toim-provetheirperformance,wecancollectlargerdatasets,learnmorepowerfulmodels,andusebet-tertechniquesforpreventingoverfitting.Untilrecently,datasetsoflabeledimageswererelativelysmall—ontheorderoftensofthou

6、sandsofimages(e.g.,NORB[16],Caltech-101/256[8,9],andCIFAR-10/100[12]).Simplerecognitiontaskscanbesolvedquitewellwithdatasetsofthissize,especiallyiftheyareaugmentedwithlabel-preservingtransformations.Forexample,thecurrent-besterrorrateontheMNISTdigit-recognitiontask(<0.3%)ap

7、proacheshumanperformance[4].Butobjectsinrealisticsettingsexhibitconsiderablevariability,sotolearntorecognizethemitisnecessarytousemuchlargertrainingsets.Andindeed,theshortcomingsofsmallimagedatasetshavebeenwidelyrecognized(e.g.,Pintoetal.[21]),butithasonlyrecentlybecomeposs

8、ibletocol-lectlabeleddatasetswithmillionsofimages.ThenewlargerdatasetsincludeLabel

当前文档最多预览五页，下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页，下载文档查看全文
温馨提示：
1. 部分包含数学公式或PPT动画的文件，查看预览时可能会显示错乱或异常，文件下载后无此问题，请放心下载。
2. 本文档由用户上传，版权归属用户，天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容，确认文档内容符合您的需求后进行下载，若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误，付费完成后未能成功下载的用户请联系客服处理。