参考说明pt0110-降维.pptxVIP

下载本文档

0
0
约1.11万字
约 47页
2022-04-28 发布于四川
举报
版权申诉

参考说明pt0110-降维.pptx

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

MPIG Open Seminar 0110 Dimensionality Reduction袁洪慧Machine Perception and Interaction Group (MPIG) .cn 公众号:mpig_robotoutlineMotivation I : Data compression Motivation II: VisualizationPrincipal component analysis problem formulationPrincipal component analysis algorithmChoosing the number of principal componentsReconstruction from compressed representationAdvice for applying PCAMotivation I:Data Compression Data CompressionReduce data from 2D to 1Dinches)((cm) Data CompressionReduce data from 2D to 1Dinches)((cm)Data CompressionReduce data from 3D to 2DX3X3Z2X2X1X2Z1X1Motivation II:Data Visualization GDPPer GDPdevelopment indexLife expectancyPoverty indexHousehold e…Canada1.5770.90880.732.667.293…China5.8787.540.6877346.910.22…India1.6323.410.54764.736.80.735…Russia1.4819.840.75565.539.90.72…Singapore0.22356.690.8668042.567.1…USA14.52746.860.9178.340.884.3……………………?Data VisualizationData VisualizationCountry1.2Canada1.60.31.7ChinaIndia1.60.21.4Russia0.50.5Singapore1.71.52USA………Data VisualizationZ2Z1Principal component analysis problem formulationPrincipal Component Analysis Problem FormulationPrincipal Component Analysis Problem FormulationReduce from 2-dimension to 1-dimension:Find a direction ( a vector ) onto which to project the data, so as to minimize the projection error. Reduce from n-dimension to k-dimension : Find k vectors ,……, onto which to project the data, so as to minimize the projection error. PCA is not linear regressionPrincipal component analysis algorithmData PreprocessingTraining set：,,…….Preprocessing ( feature scaling /mean normalization): Replace each with - .If different features on different scales ( e.g., = size of house, = number of bedrooms), scale features to have comparable range of values.=Principal Component Analysis (PCA) Algorithmp61p60Reduce data from 3D to 2DReduce data from 2D to 1DPrincipal Component Analysis (PCA) AlgorithmReduce data from n-dimensions to k-dimensionsCompute “covariance matrix”：Compute “eigenvectors”