目录 Preface1.The Need for Machine Learning DesigPatternsWhat Are DesigPatterns?How to Use This BookMachine Learning TerminologyModels and FrameworksData and Feature EngineeringThe Machine Learning ProcessData and Model ToolingRolesCommoChauenges iMachine LearningData QualityReproducibilityData DriftScaleMultiple ObjectivesSummary2.Data RepresentatioDesigPatternsSimple Data RepresentationsNumerical InputsCategorical InputsDesigPatter1: Hashed FeatureProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter2: EmbeddingsProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter3: Feature CrossProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter4: MultimodallnputProblemSolutionTrade-Offs and AlternativesSummary3.Problem RepresentatioDesigPatternsDesigPatter5: ReframingProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter6: MultilabelProblemSolutionTrade-Offs and AlternativesDesigPatter7: EnsemblesProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter8: CascadeProblemSolutionTrade-Offs and AlternativesDesigPatter9: Neutral ClassProblemSolutionWhy It WorksTrade-Offs and AlternativesDesigPatter10: Re alanangProblem……4.ModeI Training Patterns...5.DesigPatterns for Resilient Serving6.Reproduability DesigPatterns7.Responsible AI8.Connected PatternsIndex 作者介绍 Valliappa(Lak)Lakshmanan是谷歌云数据分析和人工智能解决方案的全球负责人。 Sara Robinson是谷歌云团队的开发者和倡导者,专注于机器学习。 Michael Munn是谷歌的机器学习解决方案工程师,他帮助客户设计、实现和部署机器学习模型。 序言
以下为对购买帮助不大的评价