秦晓飞系列-深度学习-1.2神经网络的编程基础ppt课件.ppt

《秦晓飞系列-深度学习-1.2神经网络的编程基础ppt课件.ppt》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、神经网络的编程基础BasicsofNeuralNetworkProgramming主讲教师：秦晓飞上海理工大学光电学院SomethingYouwillLearningthisWeekHowtoavoidusing“for”looptostepthroughmtrainingexamples.Whyalearningprocesscanbeorganizedasforwardpropagationstep,followedbybackpropagationstep.Andhowtorealizethem.Weuselogisticregressionalgorismasanex

2、ampletoprocessbinaryclassificationproblems.2.1BinaryClassification2.1BinaryClassificationIfimagesizeis64×64，incomputeritisrepresentedasy=1(cat)vs0(noncat)Unrollitintoavectorthatcanbefedintoalearningalgorism2.1BinaryClassificationNotationsusedinthesecourses2.2LogisticRegression2.2LogisticReg

3、ressionLogisticregressionisalearningalgorithmusedinasupervisedlearningproblemwhentheoutput?arealleither1or0.Thegoaloflogisticregressionistominimizetheerrorbetweenitspredictionsandtrainingdata.Example:CatvsNo-catGivenanimagerepresentedbyafeaturevector?,thealgorithmwillevaluatetheprobabilityo

4、facatbeinginthatimage.2.2LogisticRegression2.3LogisticRegressionCostFunction2.3LogisticRegressionCostFunctionNon-convexNote:thislosefunctioncanbeseenasakindofcrossentropy,whichisdefinedasameasureofsimilarityoftwodistributions.2.3LogisticRegressionCostFunctionCostfunction:tomeasurethewholetr

5、ainingseterror.Thecostfunctionistheaverageofthelossfunctionoftheentiretrainingset.Wearegoingtofindtheparameters?????thatminimizetheoverallcostfunction.2.4GradientDescent2.4GradientDescentConvex2.4GradientDescentUse1dimensiontodemonstratehowgradientdescentwork:Gradientdescentprocessinmultidi

6、mensionalspace:2.5Derivatives2.6MoreDerivativeExamples2.7ComputationGraph2.7ComputationGraphForwardpropagation:tocomputetheoutput/inference/predictBackwardpropagation:tocomputethederivativeswhichisusedtoupdateparameters.Weusecomputationgraphtocomputeforwardpropagationandbackwardpropagation.

7、2.8DerivativeswithaComputationGraph2.8DerivativeswithaComputationGraphWeusetheChainRuletorealizebackwardpropagationandcalculatethederivatives.2.9LogisticRegressionGradientDescent2.9LogisticRegressionGradientDescentLogisticregressionrecap:Suppose2.9Logist