预览加载中,请您耐心等待几秒...
1/10
2/10
3/10
4/10
5/10
6/10
7/10
8/10
9/10
10/10

亲,该文档总共23页,到这已经超出免费预览范围,如果喜欢就直接下载吧~

如果您无法下载资料,请参考说明:

1、部分资料下载需要金币,请确保您的账户上有足够的金币

2、已购买过的文档,再次下载不重复扣费

3、资料包下载后请先用软件解压,在使用对应软件打开

基于深度学习的垃圾分类方法研究 学学 学 学161203105326 · 学学2020 的的 的研究的 的 的 学学2020 基于深度学习的垃圾分类方法研究 基于深度学习垃圾分类研究 的分类类的垃圾分 类分 15%的 分分研究类的 的90%类 学学2020 Researchongarbageclassificationbasedondeeplearning Abstract Thispaperstudiesgarbageclassificationbasedondeeplearningmethods.Sinceconvolu- tionalneuralnetworksareparticularlyprominentinimagerecognitionapplications,ituses convolutionoperations,poolingoperations,localconnections,andweightsharingtoform theclassifiedmodelwhichisabrandnewconvolutionalneuralnetwork.Training,recogni- tion,classificationandpredictionoffivekindsofgarbageimageswereanalyzed.Withthe sameexperimentalconditions,comparedwiththetraditionalartificialneuralnetwork,the resultsshowthatCNNimprovestherecognitionaccuracybyabout15%.Itfindsthatthe imageresolutionisproportionaltothetime.Inthismodel,therecognitionofeachcategory isstudiedseparately,whichshowsthatthepredictedaccuracyofpaperandplasticismore than90%,whichiseasiertopredictsuccessthanothercategories. Keywords:ConvolutionalneuralnetworkArtificialneuralnetworksPoolinglayerLo- calconnection 学学2020 12 1.1........................................2 1.2.....................................2 1.3研究.................................3 2深度学习4 2.1..................................4 2.2................................5 3深度学习6 3.1垃圾.................................6 3.2................................7 3.3.....................................8 3.4.....................................9 4分11 4.1分.......