内容提要 《TensorFlow预测分析()》将通过在三个主要部分中运用TensorFlow,帮助你构建、调优和部署预测模型。部分包括预测建模所需的线性代数、统计学和概率论。第二部分包括运用监督和无监督算法开发预测模型,强化学习算法等。第三部分介绍高级预测分析的深度学习架构,包括深度神经网络以及高维和序列数据的递归神经网络。终,使用卷积神经网络进行预测建模,用于情绪识别、图像分类和情感分析。 目录 PrefaceChapter 1: Basic Pythoand Linear Algebra forPredictive AnalyticsA basic introductioto predictive analyticsWhy predictive analytics?Working principles of a predictive modelA bit of linear algebraProgramming linear algebraInstalling and getting started with PythoInstalling oWindowsInstalling PythooLinuxInstalling and upgrading PIP (or PIP3)Installing PythooMac OSInstalling packages iPythoGetting started with PythoPythodata typesUsing strings iPythoUsing lists iPythoUsing tuples iPythoUsing dictionary iPythoUsing sets iPythoFunctions iPythoClasses iPythoVectors, matrices, and graphsVectorsMatricesMatrix additioMatrix subtractioFinding the determinant of a matrixFinding the transpose of a matrixSolving simultaneous linear equationsEigenvalues and eigenvectorsSpaand linear independencePrincipal component analysisSingular value decompositioData compressioia predictive model using SVDPredictive analytics tools iPythoSummaryChapter 2: Statistics, Probability, and InformatioTheory forPredictive ModelingUsing statistics ipredictive modelingStatistical modelsParametric versus nonparametric modelPopulatioand sampleRandom samplingExpectatioCentral limit theoremSkewness and data distributioStandard deviatioand varianceCovariance and correlatioInterquartile, range, and quartilesHypothesis testingChi-square testsChi-square independence testBasic probability for predictive modelingProbability and the random variablesGenerating random numbers and setting the seedProbability distributionsMarginal probabilityConditional probabilityThe chairule of conditional probabilityIndependence and conditional independenceBayes' ruleUsing informatiotheory ipredictive modelingSelf-informatioMutual informatioEntropyShannoentropyJoint entropyConditional entropyInformatiogaiUsing informatiotheory……Chapter 3: From Data to Decisions - Getting Started with TensorFlowChapter 4: Putting Data iPlace -Supervised Learning for Predictive AnalvticsChapter 5: Clustering Your Data - Unsupervised Learning for Predictive AnalyticsChapter 6: Predictive Analytics Pipelines for NLPChapter 7: Using Deep Neural Networks for Predictive AnalyticsChapter 8: Using Convolutional Neural Networks for Predictive AnalvticsChapter 9: Using Recurrent Neural Networks for Predictive AnalyticsChapter 10: RecommendatioSystems for Predictive AnalyticsChapter 11: Using Reinforcement Learning for Predictive Analytics...... 作者介绍
序言 PrefaceChapter 1: Basic Pythoand Linear Algebra forPredictive AnalyticsA basic introductioto predictive analyticsWhy predictive analytics?Working principles of a predictive modelA bit of linear algebraProgramming linear algebraInstalling and getting started with PythonInstalling oWindowsInstalling PythooLinuxInstalling and upgrading PIP (or PIP3)Installing PythooMac OSInstalling packages iPythonGetting started with PythonPythodata typesUsing strings iPythonUsing lists iPythonUsing tuples iPythonUsing dictionary iPythonUsing sets iPythonFunctions iPythonClasses iPythonVectors, matrices, and graphsVectorsMatricesMatrix additionMatrix subtractionFinding the determinant of a matrixFinding the transpose of a matrixSolving simultaneous linear equationsEigenvalues and eigenvectorsSpaand linear independencePrincipal component analysisSingular value decompositionData compressioia predictive model using SVDPredictive analytics tools iPythonSummaryChapter 2: Statistics, Probability, and InformatioTheory forPredictive ModelingUsing statistics ipredictive modelingStatistical modelsParametric versus nonparametric modelPopulatioand sampleRandom samplingExpectationCentral limit theoremSkewness and data distributionStandard deviatioand varianceCovariance and correlationInterquartile, range, and quartilesHypothesis testingChi-square testsChi-square independence testBasic probability for predictive modelingProbability and the random variablesGenerating random numbers and setting the seedProbability distributionsMarginal probabilityConditional probabilityThe chairule of conditional probabilityIndependence and conditional independenceBayes' ruleUsing informatiotheory ipredictive modelingSelf-informationMutual informationEntropyShannoentropyJoint entropyConditional entropyInformatiogainUsing informatiotheory……Chapter 3: From Data to Decisions - Getting Started with TensorFlowChapter 4: Putting Data iPlace -Supervised Learning for Predictive AnalvticsChapter 5: Clustering Your Data - Unsupervised Learning for Predictive AnalyticsChapter 6: Predictive Analytics Pipelines for NLPChapter 7: Using Deep Neural Networks for Predictive AnalyticsChapter 8: Using Convolutional Neural Networks for Predictive AnalvticsChapter 9: Using Recurrent Neural Networks for Predictive AnalyticsChapter 10: RecommendatioSystems for Predictive AnalyticsChapter 11: Using Reinforcement Learning for Predictive Analytics......
以下为对购买帮助不大的评价