控制理论和最优滤波器设计的经典教材，有很强的专业性，适合控制理论和信号处理方面的进阶。

利用PSO训练BP神经网络的matlab代码。
粒子群算法优化BP神经网络，可用于指标预测(BPneuralnetworkoptimizedbyParticleswarmoptimization(PSO)thatcanbeusedforindexprediction)

在predictionio推荐框架上直接访问Hbase事件存储，实现事件的批量上传、删除及查询，

PartIMetricSearchinginaNutshellOverview31.FOUNDATIONSOFMETRICSPACESEARCHING51TheDistanceSearchingProblem62TheMetricSpace83DistanceMeasures93.1MinkowskiDistances103.2QuadraticFormDistance113.3EditDistance123.4TreeEditDistance133.5Jaccard’sCoefficient133.6HausdorffDistance143.7TimeComplexity144SimilarityQueries154.1RangeQuery154.2NearestNeighborQuery164.3ReverseNearestNeighborQuery174.4SimilarityJoin174.5CombinationsofQueries184.6ComplexSimilarityQueries185BasicPartitioningPrinciples205.1BallPartitioning205.2GeneralizedHyperplanePartitioning215.3ExcludedMiddlePartitioning215.4Extensions216PrinciplesofSimilarityQueryExecution226.1BasicStrategies226.2IncrementalSimilaritySearch257PoliciesforAvoidingDistanceComputations267.1ExplanatoryExample277.2Object-PivotDistanceConstraint287.3Range-PivotDistanceConstraint307.4Pivot-PivotDistanceConstraint317.5Double-PivotDistanceConstraint337.6PivotFiltering348MetricSpaceTransformations358.1MetricHierarchies368.1.1Lower-BoundingFunctions368.2User-DefinedMetricFunctions388.2.1SearchingUsingLower-BoundingFunctions388.3EmbeddingMetricSpace398.3.1EmbeddingExamples398.3.2ReducingDimensionality409ApproximateSimilaritySearch419.1Principles419.2GenericAlgorithms449.3MeasuresofPerformance469.3.1ImprovementinEfficiency469.3.2PrecisionandRecall469.3.3RelativeErroronDistances489.3.4PositionError4910AdvancedIssues5010.1StatisticsonMetricDatasets5110.1.1DistributionandDensityFunctions5110.1.2DistanceDistributionandDensity5210.1.3HomogeneityofViewpoints5410.2ProximityofBallRegions5510.3PerformancePrediction58Contentsix10.4TreeQualityMeasures6010.5ChoosingReferencePoints632.SURVEYOFEXISTINGAPPROACHES671BallPartitioningMethods671.1Burkhard-KellerTree6

Overthepastfewdecades,mathematicalmodelshavebecomeanincreasinglyimportanttoolforEarthscientiststounderstandandmakepredictionsabouthowourplanetfunctionsandevolvesthroughtimeandspace.Thesemodelsoftenconsistofpartialdifferentialequations(PDEs)thatarediscretizedwithanumericalmethodandsolvedonacomputer.Themostcommonlyuseddiscretizationmethodsarethefinitedifferencemethod(FDM),thefinitevolumemethod,thefiniteelementmethod(FEM),thediscreteelementmethod,theboundaryelementmethod,andvariousspectralmethods.

I'mgladyou'rehere.It'sabouttimewetalkedaboutmachinelearning.Machinelearningisnolongerjustabuzzword,itisallaroundus:fromprotectingyouremail,toautomaticallytaggingfriendsinpictures,topredictingwhatmoviesyoulike.Asasubfieldofdatascience,machinelearningenablescomputerstolearnthroughexperience:tomakepredictionsaboutthefutureusingcollecteddatafromthepast.Andtheamountofdatatobeanalyzedisenormous!Currentestimatesputthedailyamountofproduceddataat2.5exabytes(orroughly1billiongigabytes).Canyoubelieveit?Thiswouldbeenoughdatatofillup10millionblu-raydiscs,oramountto90yearsofHDvideo.Inordertodealwiththisvastamountofdata,companiessuchasGoogle,Amazon,Microsoft,andFacebookhavebeenheavilyinvestinginthedevelopmentofdatascienceplatformsthatallowustobenefitfrommachinelearningwhereverwego—scalingfromyourmobilephoneapplicationallthewaytosupercomputersconnectedthroughthecloud.

ThisisasmalllibrarythatcantrainRestrictedBoltzmannMachines,andalsoDeepBeliefNetworksofstackedRBM's.TrainRBM's:%trainanRBMwithbinaryvisibleunitsand500binaryhiddenmodel=rbmBB(data,500);%visualizethelearnedweightsvisualize(model.W);Doclassification:model=rbmFit(data,500,labels);prediction=rbmPredict(model,testdata);TrainaDeepBeliefNetworkwith500,500,2000architectureforclassification:models=dbnFit(data,[5005002000],labels);prediction=dbnPredict(models,testdata);seeincludedexamplecodeformoreIcanbecontactedonandrej.karpathy@gmail.NOTE:ThiswasaclassprojectthatIworkedonfor1monthandthenabandoneddevelopmentforalmost4yearsago.Pleasedonotsendmespecificquestionsaboutissueswiththecodeorquestionsonhowtodosomething.Ionlyputthiscodeonlineinhopethatitcanbeusefultoothersbutcannotfullysupportit.Ifyouwouldlikepointerstomoreactivelymaintainedimplementations,havealookhere(https://github.com/rasmusbergpalm/DeepLearnToolbox)ormaybehere(https://github.com/lisa-lab/DeepLearningTutorials)Sorryandbestofluck!原文：http://code.google.com/p/matrbm/

《TheElementsofStatisticalLearning-DataMining,Inference,andPrediction》英文原版教材第二版

Inresponsetotheexponentiallyincreasingneedtoanalyzevastamountsofdata,NeuralNetworksforAppliedSciencesandEngineering:FromFundamentalstoComplexPatternRecognitionprovidesscientistswithasimplebutsystematicintroductiontoneuralnetworks.Beginningwithanintroductorydiscussionontheroleofneuralnetworksinscientificdataanalysis,thisbookprovidesasolidfoundationofbasicneuralnetworkconcepts.Itcontainsanoverviewofneuralnetworkarchitecturesforpracticaldataanalysisfollowedbyextensivestep-by-stepcoverageonlinearnetworks,aswellas,multi-layerperceptronfornonlinearpredictionandclassificationexplainingallstagesofprocessingandmodeldevelopmentillustratedthroughpracticalexamplesandcasestudies.LaterchapterspresentanextensivecoverageonSelfOrganizingMapsfornonlineardataclustering,recurrentnetworksforlinearnonlineartimeseriesforecasting,andothernetworktypessuitableforscientificdataanalysis.Withaneasytounderstandformatusingextensivegraphicalillustrationsandmultidisciplinaryscientificcontext,thisbookfillsthegapinthemarketforneuralnetworksformulti-dimensionalscientificdata,andrelatesneuralnetworkstostatistics.FeaturesxExplainsneuralnetworksinamulti-disciplinarycontextxUsesextensivegraphicalillustrationstoexplaincomplexmathematicalconceptsforquickandeasyunderstanding?Examinesin-depthneuralnetworksforlinearandnonlinearprediction,classification,clusteringandforecastingxIllustratesallstagesofmodeldevelopmentandinterpretationofresults,includingdatapreprocessing,datadimensionalityreduction,inputselection,modeldevelopmentandvalidation,modeluncertaintyassessment,sensitivityanalysesoninputs,errorsandmodelparametersSandhyaSamarasingheobtainedherMScinMechanicalEngineeringfromLumumbaUniversityinRussiaandanMSandPhDinEngineeringfromVirginiaTech,USA.

kaggle比赛数据集：Porto_Seguro’s_Safe_Driver_Prediction_all.zipPorto_Seguro’s_Safe_Driver_Prediction_all.zip

在日常工作中，钉钉打卡成了我生活中不可或缺的一部分。然而，有时候这个看似简单的任务却给我带来了不少烦恼。 每天早晚，我总是得牢记打开钉钉应用，点击"工作台"，再找到"考勤打卡"进行签到。有时候因为工作忙碌，会忘记打卡，导致考勤异常，影响当月的工作评价。而且，由于我使用的是苹果手机，有时候系统更新后，钉钉的某些功能会出现异常，使得打卡变得更加麻烦。 另外，我的家人使用的是安卓手机，他们也经常抱怨钉钉打卡的繁琐。尤其是对于那些不太熟悉手机操作的长辈来说，每次打卡都是一次挑战。他们总是担心自己会操作失误，导致打卡失败。 为了解决这些烦恼，我开始思考是否可以通过编写一个全自动化脚本来实现钉钉打卡。经过一段时间的摸索和学习，我终于成功编写出了一个适用于苹果和安卓系统的钉钉打卡脚本。