semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning

semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning

ID:11364763

大小:49.00 KB

页数:11页

时间:2018-07-11

semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning_第1页
semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning_第2页
semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning_第3页
semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning_第4页
semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning_第5页
资源描述:

《semiconductor yield analysis and multi-chip package (mcp) die pairing optimization using machine learning》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、SemiconductorYieldAnalysisandMulti-ChipPackage(MCP)DiePairingOptimizationusingMachineLearningSemiconductorYieldAnalysisandMulti—ChipPackage(MCP)DiePairingOptimizationusingMachineLearningRandallGoodwin,TechnologyandManufacturingGroup,IntelCorporationRussellMille

2、r,TechnologyandManufacturingGroup,IntelCorporationEugeneTuv,TechnologyandManufacturingGroup,IntelCorporationAlexanderBorisov,TechnologyandManufacturingGroup,IntelCorporationIndexWords:statistics,machinelearning,datamining,optimizationAbstractMachineLearning,Art

3、ificia1Intelligence(AI)andStatisticalLearningarerelatedmathematicalfeldswhichutilizecomputeralgorithmstocreatemodelsforthepumosesofdatadescriptionand/orprediction.Somewellknownexamplesincludebiometricidentificationandauthorizationsystems,speechrecognitionanduse

4、rtargetedinternetadvertising.StatisticalLearning.whichwewilluseinthispaper,alsohasmanyapplicationsinsemiconductormanufacturing.Someofthechallengingcharacteristicsofsemiconductordataincludehighdimensionality,mixturesofcategoricalandnumericdata,non—randomlymissin

5、gdata,non—Gaussianandmultimodaldistributions.nonlinearcomplexrelationships,noise,outliersandtemporaldependencies.Thesechallengesarebecomingparticularlyacuteasthequantityofavailabledataincreasesandtheabilitytotracelots,wafers,die,andpackagesthroughoutthefullfab.

6、wafertest.assemblyandfinaltestmanufacturingflowimproves.Statistical—learningtechniquesareappliedtoaddressthesechallenges.InthispaperwediscusstheadvancementandapplicationsofTreebasedclassificationandregressionmethodstosemiconductordata.WebeginthePaDerwithadescri

7、ptionoftheproblem,followedbyanoverviewofthestatistical—learningtechniquesweuseinourcasestudies.Wethendescribehowthechallengespresentedbysemiconductordatawereaddressedwithoriginalextensionstotree—basedandkernel—basedmethods.Next,wereviewfourcasestudies:homesales

8、priceprediction,signalidentification/separation,finalspeedbinclassificationanddiepairingoptimizationforMulti—ChipPackages(MCP).Resultsfromthecasestudiesdemonstratehowstatist

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。