{"product_id":"official-google-cloud-certified-professional-machine-learning-engineer-study-guide-isbn-9781119944461","title":"Official Google Cloud Certified Professional Machine Learning Engineer Study Guide","description":"\u003cp\u003e\u003cb\u003eExpert, guidance for the Google Cloud Machine Learning certification exam\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eIn \u003ci\u003eGoogle Cloud Certified Professional Machine Learning Study Guide\u003c\/i\u003e, a team of accomplished artificial intelligence (AI) and machine learning (ML) specialists delivers an expert roadmap to AI and ML on the Google Cloud Platform based on new exam curriculum. With Sybex, you’ll prepare faster and smarter for the Google Cloud Certified Professional Machine Learning Engineer exam and get ready to hit the ground running on your first day at your new job as an ML engineer. \u003c\/p\u003e\u003cp\u003eThe book walks readers through the machine learning process from start to finish, starting with data, feature engineering, model training, and deployment on Google Cloud. It also discusses best practices on when to pick a custom model vs AutoML or pretrained models with Vertex AI platform. All technologies such as Tensorflow, Kubeflow, and Vertex AI are presented by way of real-world scenarios to help you apply the theory to practical examples and show you how IT professionals design, build, and operate secure ML cloud environments. \u003c\/p\u003e\u003cp\u003eThe book also shows you how to: \u003c\/p\u003e\u003cul\u003e \u003cli\u003eFrame ML problems and architect ML solutions from scratch\u003c\/li\u003e \u003cli\u003eBanish test anxiety by verifying and checking your progress with built-in self-assessments and other practical tools\u003c\/li\u003e \u003cli\u003eUse the Sybex online practice environment, complete with practice questions and explanations, a glossary, objective maps, and flash cards\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eA can’t-miss resource for everyone preparing for the Google Cloud Certified Professional Machine Learning certification exam, or for a new career in ML powered by the Google Cloud Platform, this Sybex \u003ci\u003eStudy Guide\u003c\/i\u003e has everything you need to take the next step in your career. \u003c\/p\u003e\u003cp\u003eIntroduction xxi\u003c\/p\u003e \u003cp\u003eAssessment Testxxxii\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Framing ML Problems 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTranslating Business Use Cases 3\u003c\/p\u003e \u003cp\u003eMachine Learning Approaches 5\u003c\/p\u003e \u003cp\u003eSupervised, Unsupervised, and Semi- supervised Learning 5\u003c\/p\u003e \u003cp\u003eClassification, Regression, Forecasting, and Clustering 7\u003c\/p\u003e \u003cp\u003eML Success Metrics 8\u003c\/p\u003e \u003cp\u003eRegression 12\u003c\/p\u003e \u003cp\u003eResponsible AI Practices 13\u003c\/p\u003e \u003cp\u003eSummary 14\u003c\/p\u003e \u003cp\u003eExam Essentials 14\u003c\/p\u003e \u003cp\u003eReview Questions 15\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Exploring Data and Building Data Pipelines 19\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eVisualization 20\u003c\/p\u003e \u003cp\u003eBox Plot 20\u003c\/p\u003e \u003cp\u003eLine Plot 21\u003c\/p\u003e \u003cp\u003eBar Plot 21\u003c\/p\u003e \u003cp\u003eScatterplot 22\u003c\/p\u003e \u003cp\u003eStatistics Fundamentals 22\u003c\/p\u003e \u003cp\u003eMean 22\u003c\/p\u003e \u003cp\u003eMedian 22\u003c\/p\u003e \u003cp\u003eMode 23\u003c\/p\u003e \u003cp\u003eOutlier Detection 23\u003c\/p\u003e \u003cp\u003eStandard Deviation 23\u003c\/p\u003e \u003cp\u003eCorrelation 24\u003c\/p\u003e \u003cp\u003eData Quality and Reliability 24\u003c\/p\u003e \u003cp\u003eData Skew 25\u003c\/p\u003e \u003cp\u003eData Cleaning 25\u003c\/p\u003e \u003cp\u003eScaling 25\u003c\/p\u003e \u003cp\u003eLog Scaling 26\u003c\/p\u003e \u003cp\u003eZ-score 26\u003c\/p\u003e \u003cp\u003eClipping 26\u003c\/p\u003e \u003cp\u003eHandling Outliers 26\u003c\/p\u003e \u003cp\u003eEstablishing Data Constraints 27\u003c\/p\u003e \u003cp\u003eExploration and Validation at Big- Data Scale 27\u003c\/p\u003e \u003cp\u003eRunning TFDV on Google Cloud Platform 28\u003c\/p\u003e \u003cp\u003eOrganizing and Optimizing Training Datasets 29\u003c\/p\u003e \u003cp\u003eImbalanced Data 29\u003c\/p\u003e \u003cp\u003eData Splitting 31\u003c\/p\u003e \u003cp\u003eData Splitting Strategy for Online Systems 31\u003c\/p\u003e \u003cp\u003eHandling Missing Data 32\u003c\/p\u003e \u003cp\u003eData Leakage 33\u003c\/p\u003e \u003cp\u003eSummary 34\u003c\/p\u003e \u003cp\u003eExam Essentials 34\u003c\/p\u003e \u003cp\u003eReview Questions 36\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Feature Engineering 39\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eConsistent Data Preprocessing 40\u003c\/p\u003e \u003cp\u003eEncoding Structured Data Types 41\u003c\/p\u003e \u003cp\u003eMapping Numeric Values 42\u003c\/p\u003e \u003cp\u003eMapping Categorical Values 42\u003c\/p\u003e \u003cp\u003eFeature Selection 44\u003c\/p\u003e \u003cp\u003eClass Imbalance 44\u003c\/p\u003e \u003cp\u003eClassification Threshold with Precision and Recall 45\u003c\/p\u003e \u003cp\u003eArea under the Curve (AUC) 46\u003c\/p\u003e \u003cp\u003eFeature Crosses 46\u003c\/p\u003e \u003cp\u003eTensorFlow Transform 49\u003c\/p\u003e \u003cp\u003eTensorFlow Data API (tf.data) 49\u003c\/p\u003e \u003cp\u003eTensorFlow Transform 49\u003c\/p\u003e \u003cp\u003eGCP Data and ETL Tools 51\u003c\/p\u003e \u003cp\u003eSummary 51\u003c\/p\u003e \u003cp\u003eExam Essentials 52\u003c\/p\u003e \u003cp\u003eReview Questions 53\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Choosing the Right ML Infrastructure 57\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003ePretrained vs. AutoML vs. Custom Models 58\u003c\/p\u003e \u003cp\u003ePretrained Models 60\u003c\/p\u003e \u003cp\u003eVision AI 61\u003c\/p\u003e \u003cp\u003eVideo AI 62\u003c\/p\u003e \u003cp\u003eNatural Language AI 62\u003c\/p\u003e \u003cp\u003eTranslation AI 63\u003c\/p\u003e \u003cp\u003eSpeech- to- Text 63\u003c\/p\u003e \u003cp\u003eText- to- Speech 64\u003c\/p\u003e \u003cp\u003eAutoML 64\u003c\/p\u003e \u003cp\u003eAutoML for Tables or Structured Data 64\u003c\/p\u003e \u003cp\u003eAutoML for Images and Video 66\u003c\/p\u003e \u003cp\u003eAutoML for Text 67\u003c\/p\u003e \u003cp\u003eRecommendations AI\/Retail AI 68\u003c\/p\u003e \u003cp\u003eDocument AI 69\u003c\/p\u003e \u003cp\u003eDialogflow and Contact Center AI 69\u003c\/p\u003e \u003cp\u003eCustom Training 70\u003c\/p\u003e \u003cp\u003eHow a CPU Works 71\u003c\/p\u003e \u003cp\u003eGPU 71\u003c\/p\u003e \u003cp\u003eTPU 72\u003c\/p\u003e \u003cp\u003eProvisioning for Predictions 74\u003c\/p\u003e \u003cp\u003eScaling Behavior 75\u003c\/p\u003e \u003cp\u003eFinding the Ideal Machine Type 75\u003c\/p\u003e \u003cp\u003eEdge TPU 76\u003c\/p\u003e \u003cp\u003eDeploy to Android or iOS Device 76\u003c\/p\u003e \u003cp\u003eSummary 77\u003c\/p\u003e \u003cp\u003eExam Essentials 77\u003c\/p\u003e \u003cp\u003eReview Questions 78\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Architecting ML Solutions 83\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eDesigning Reliable, Scalable, and Highly Available ml Solutions 84\u003c\/p\u003e \u003cp\u003eChoosing an Appropriate ML Service 86\u003c\/p\u003e \u003cp\u003eData Collection and Data Management 87\u003c\/p\u003e \u003cp\u003eGoogle Cloud Storage (GCS) 88\u003c\/p\u003e \u003cp\u003eBigQuery 88\u003c\/p\u003e \u003cp\u003eVertex AI Managed Datasets 89\u003c\/p\u003e \u003cp\u003eVertex AI Feature Store 89\u003c\/p\u003e \u003cp\u003eNoSQL Data Store 90\u003c\/p\u003e \u003cp\u003eAutomation and Orchestration 91\u003c\/p\u003e \u003cp\u003eUse Vertex AI Pipelines to Orchestrate the ML Workflow 92\u003c\/p\u003e \u003cp\u003eUse Kubeflow Pipelines for Flexible Pipeline Construction 92\u003c\/p\u003e \u003cp\u003eUse TensorFlow Extended SDK to Leverage Pre-built Components for Common Steps 93\u003c\/p\u003e \u003cp\u003eWhen to Use Which Pipeline 93\u003c\/p\u003e \u003cp\u003eServing 94\u003c\/p\u003e \u003cp\u003eOffline or Batch Prediction 94\u003c\/p\u003e \u003cp\u003eOnline Prediction 95\u003c\/p\u003e \u003cp\u003eSummary 97\u003c\/p\u003e \u003cp\u003eExam Essentials 97\u003c\/p\u003e \u003cp\u003eReview Questions 98\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Building Secure ML Pipelines 103\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBuilding Secure ML Systems 104\u003c\/p\u003e \u003cp\u003eEncryption at Rest 104\u003c\/p\u003e \u003cp\u003eEncryption in Transit 105\u003c\/p\u003e \u003cp\u003eEncryption in Use 105\u003c\/p\u003e \u003cp\u003eIdentity and Access Management 105\u003c\/p\u003e \u003cp\u003eIAM Permissions for Vertex AI Workbench 106\u003c\/p\u003e \u003cp\u003eSecuring a Network with Vertex AI 109\u003c\/p\u003e \u003cp\u003ePrivacy Implications of Data Usage and Collection 113\u003c\/p\u003e \u003cp\u003eGoogle Cloud Data Loss Prevention 114\u003c\/p\u003e \u003cp\u003eGoogle Cloud Healthcare API for PHI Identification 115\u003c\/p\u003e \u003cp\u003eBest Practices for Removing Sensitive Data 116\u003c\/p\u003e \u003cp\u003eSummary 117\u003c\/p\u003e \u003cp\u003eExam Essentials 118\u003c\/p\u003e \u003cp\u003eReview Questions 119\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Model Building 121\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eChoice of Framework and Model Parallelism 122\u003c\/p\u003e \u003cp\u003eData Parallelism 122\u003c\/p\u003e \u003cp\u003eModel Parallelism 123\u003c\/p\u003e \u003cp\u003eModeling Techniques 125\u003c\/p\u003e \u003cp\u003eArtificial Neural Network 126\u003c\/p\u003e \u003cp\u003eDeep Neural Network (DNN) 126\u003c\/p\u003e \u003cp\u003eConvolutional Neural Network 126\u003c\/p\u003e \u003cp\u003eRecurrent Neural Network 127\u003c\/p\u003e \u003cp\u003eWhat Loss Function to Use 127\u003c\/p\u003e \u003cp\u003eGradient Descent 128\u003c\/p\u003e \u003cp\u003eLearning Rate 129\u003c\/p\u003e \u003cp\u003eBatch 129\u003c\/p\u003e \u003cp\u003eBatch Size 129\u003c\/p\u003e \u003cp\u003eEpoch 129\u003c\/p\u003e \u003cp\u003eHyperparameters 129\u003c\/p\u003e \u003cp\u003eTransfer Learning 130\u003c\/p\u003e \u003cp\u003eSemi-supervised Learning 131\u003c\/p\u003e \u003cp\u003eWhen You Need Semi-supervised Learning 131\u003c\/p\u003e \u003cp\u003eLimitations of SSL 131\u003c\/p\u003e \u003cp\u003eData Augmentation 132\u003c\/p\u003e \u003cp\u003eOffline Augmentation 132\u003c\/p\u003e \u003cp\u003eOnline Augmentation 132\u003c\/p\u003e \u003cp\u003eModel Generalization and Strategies to Handle Overfitting and Underfitting 133\u003c\/p\u003e \u003cp\u003eBias Variance Trade- Off 133\u003c\/p\u003e \u003cp\u003eUnderfitting 133\u003c\/p\u003e \u003cp\u003eOverfitting 134\u003c\/p\u003e \u003cp\u003eRegularization 134\u003c\/p\u003e \u003cp\u003eSummary 136\u003c\/p\u003e \u003cp\u003eExam Essentials 137\u003c\/p\u003e \u003cp\u003eReview Questions 138\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Model Training and Hyperparameter Tuning 143\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eIngestion of Various File Types into Training 145\u003c\/p\u003e \u003cp\u003eCollect 146\u003c\/p\u003e \u003cp\u003eProcess 147\u003c\/p\u003e \u003cp\u003eStore and Analyze 150\u003c\/p\u003e \u003cp\u003eDeveloping Models in Vertex AI Workbench by Using Common Frameworks 151\u003c\/p\u003e \u003cp\u003eCreating a Managed Notebook 153\u003c\/p\u003e \u003cp\u003eExploring Managed JupyterLab Features 154\u003c\/p\u003e \u003cp\u003eData Integration 155\u003c\/p\u003e \u003cp\u003eBigQuery Integration 155\u003c\/p\u003e \u003cp\u003eAbility to Scale the Compute Up or Down 156\u003c\/p\u003e \u003cp\u003eGit Integration for Team Collaboration 156\u003c\/p\u003e \u003cp\u003eSchedule or Execute a Notebook Code 158\u003c\/p\u003e \u003cp\u003eCreating a User-Managed Notebook 159\u003c\/p\u003e \u003cp\u003eTraining a Model as a Job in Different Environments 161\u003c\/p\u003e \u003cp\u003eTraining Workflow with Vertex AI 162\u003c\/p\u003e \u003cp\u003eTraining Dataset Options in Vertex AI 163\u003c\/p\u003e \u003cp\u003ePre-built Containers 163\u003c\/p\u003e \u003cp\u003eCustom Containers 166\u003c\/p\u003e \u003cp\u003eDistributed Training 168\u003c\/p\u003e \u003cp\u003eHyperparameter Tuning 169\u003c\/p\u003e \u003cp\u003eWhy Hyperparameters Are Important 170\u003c\/p\u003e \u003cp\u003eTechniques to Speed Up Hyperparameter Optimization 171\u003c\/p\u003e \u003cp\u003eHow Vertex AI Hyperparameter Tuning Works 171\u003c\/p\u003e \u003cp\u003eVertex AI Vizier 174\u003c\/p\u003e \u003cp\u003eTracking Metrics During Training 175\u003c\/p\u003e \u003cp\u003eInteractive Shell 175\u003c\/p\u003e \u003cp\u003eTensorFlow Profiler 177\u003c\/p\u003e \u003cp\u003eWhat-If Tool 177\u003c\/p\u003e \u003cp\u003eRetraining\/Redeployment Evaluation 178\u003c\/p\u003e \u003cp\u003eData Drift 178\u003c\/p\u003e \u003cp\u003eConcept Drift 178\u003c\/p\u003e \u003cp\u003eWhen Should a Model Be Retrained? 178\u003c\/p\u003e \u003cp\u003eUnit Testing for Model Training and Serving 179\u003c\/p\u003e \u003cp\u003eTesting for Updates in API Calls 180\u003c\/p\u003e \u003cp\u003eTesting for Algorithmic Correctness 180\u003c\/p\u003e \u003cp\u003eSummary 180\u003c\/p\u003e \u003cp\u003eExam Essentials 181\u003c\/p\u003e \u003cp\u003eReview Questions 182\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Model Explainability on Vertex AI 187\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eModel Explainability on Vertex AI 188\u003c\/p\u003e \u003cp\u003eExplainable AI 188\u003c\/p\u003e \u003cp\u003eInterpretability and Explainability 189\u003c\/p\u003e \u003cp\u003eFeature Importance 189\u003c\/p\u003e \u003cp\u003eVertex Explainable AI 189\u003c\/p\u003e \u003cp\u003eData Bias and Fairness 193\u003c\/p\u003e \u003cp\u003eML Solution Readiness 194\u003c\/p\u003e \u003cp\u003eHow to Set Up Explanations in the Vertex AI 195\u003c\/p\u003e \u003cp\u003eSummary 196\u003c\/p\u003e \u003cp\u003eExam Essentials 196\u003c\/p\u003e \u003cp\u003eReview Questions 197\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 Scaling Models in Production 199\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eScaling Prediction Service 200\u003c\/p\u003e \u003cp\u003eTensorFlow Serving 201\u003c\/p\u003e \u003cp\u003eServing (Online, Batch, and Caching) 203\u003c\/p\u003e \u003cp\u003eReal- Time Static and Dynamic Reference Features 203\u003c\/p\u003e \u003cp\u003ePre-computing and Caching Prediction 206\u003c\/p\u003e \u003cp\u003eGoogle Cloud Serving Options 207\u003c\/p\u003e \u003cp\u003eOnline Predictions 207\u003c\/p\u003e \u003cp\u003eBatch Predictions 212\u003c\/p\u003e \u003cp\u003eHosting Third- Party Pipelines (MLFlow) on Google Cloud 213\u003c\/p\u003e \u003cp\u003eTesting for Target Performance 214\u003c\/p\u003e \u003cp\u003eConfiguring Triggers and Pipeline Schedules 215\u003c\/p\u003e \u003cp\u003eSummary 216\u003c\/p\u003e \u003cp\u003eExam Essentials 217\u003c\/p\u003e \u003cp\u003eReview Questions 218\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 Designing ML Training Pipelines 221\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eOrchestration Frameworks 223\u003c\/p\u003e \u003cp\u003eKubeflow Pipelines 224\u003c\/p\u003e \u003cp\u003eVertex AI Pipelines 225\u003c\/p\u003e \u003cp\u003eApache Airflow 228\u003c\/p\u003e \u003cp\u003eCloud Composer 229\u003c\/p\u003e \u003cp\u003eComparison of Tools 229\u003c\/p\u003e \u003cp\u003eIdentification of Components, Parameters, Triggers, and Compute Needs 230\u003c\/p\u003e \u003cp\u003eSchedule the Workflows with Kubeflow Pipelines 230\u003c\/p\u003e \u003cp\u003eSchedule Vertex AI Pipelines 232\u003c\/p\u003e \u003cp\u003eSystem Design with Kubeflow\/TFX 232\u003c\/p\u003e \u003cp\u003eSystem Design with Kubeflow DSL 232\u003c\/p\u003e \u003cp\u003eSystem Design with TFX 234\u003c\/p\u003e \u003cp\u003eHybrid or Multicloud Strategies 235\u003c\/p\u003e \u003cp\u003eSummary 236\u003c\/p\u003e \u003cp\u003eExam Essentials 237\u003c\/p\u003e \u003cp\u003eReview Questions 238\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 12 Model Monitoring, Tracking, and Auditing Metadata 241\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eModel Monitoring 242\u003c\/p\u003e \u003cp\u003eConcept Drift 242\u003c\/p\u003e \u003cp\u003eData Drift 243\u003c\/p\u003e \u003cp\u003eModel Monitoring on Vertex AI 243\u003c\/p\u003e \u003cp\u003eDrift and Skew Calculation 244\u003c\/p\u003e \u003cp\u003eInput Schemas 245\u003c\/p\u003e \u003cp\u003eLogging Strategy 247\u003c\/p\u003e \u003cp\u003eTypes of Prediction Logs 247\u003c\/p\u003e \u003cp\u003eLog Settings 248\u003c\/p\u003e \u003cp\u003eModel Monitoring and Logging 248\u003c\/p\u003e \u003cp\u003eModel and Dataset Lineage 249\u003c\/p\u003e \u003cp\u003eVertex ML Metadata 249\u003c\/p\u003e \u003cp\u003eVertex AI Experiments 252\u003c\/p\u003e \u003cp\u003eVertex AI Debugging 253\u003c\/p\u003e \u003cp\u003eSummary 253\u003c\/p\u003e \u003cp\u003eExam Essentials 254\u003c\/p\u003e \u003cp\u003eReview Questions 255\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 13 Maintaining ML Solutions 259\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMLOps Maturity 260\u003c\/p\u003e \u003cp\u003eMLOps Level 0: Manual\/Tactical Phase 261\u003c\/p\u003e \u003cp\u003eMLOps Level 1: Strategic Automation Phase 263\u003c\/p\u003e \u003cp\u003eMLOps Level 2: CI\/CD Automation, Transformational Phase 264\u003c\/p\u003e \u003cp\u003eRetraining and Versioning Models 266\u003c\/p\u003e \u003cp\u003eTriggers for Retraining 267\u003c\/p\u003e \u003cp\u003eVersioning Models 267\u003c\/p\u003e \u003cp\u003eFeature Store 268\u003c\/p\u003e \u003cp\u003eSolution 268\u003c\/p\u003e \u003cp\u003eData Model 269\u003c\/p\u003e \u003cp\u003eIngestion and Serving 269\u003c\/p\u003e \u003cp\u003eVertex AI Permissions Model 270\u003c\/p\u003e \u003cp\u003eCustom Service Account 270\u003c\/p\u003e \u003cp\u003eAccess Transparency in Vertex AI 271\u003c\/p\u003e \u003cp\u003eCommon Training and Serving Errors 271\u003c\/p\u003e \u003cp\u003eTraining Time Errors 271\u003c\/p\u003e \u003cp\u003eServing Time Errors 271\u003c\/p\u003e \u003cp\u003eTensorFlow Data Validation 272\u003c\/p\u003e \u003cp\u003eVertex AI Debugging Shell 272\u003c\/p\u003e \u003cp\u003eSummary 272\u003c\/p\u003e \u003cp\u003eExam Essentials 273\u003c\/p\u003e \u003cp\u003eReview Questions 274\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 14 BigQuery ML 279\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBigQuery – Data Access 280\u003c\/p\u003e \u003cp\u003eBigQuery ML Algorithms 282\u003c\/p\u003e \u003cp\u003eModel Training 282\u003c\/p\u003e \u003cp\u003eModel Evaluation 284\u003c\/p\u003e \u003cp\u003ePrediction 285\u003c\/p\u003e \u003cp\u003eExplainability in BigQuery ML 286\u003c\/p\u003e \u003cp\u003eBigQuery ML vs. Vertex AI Tables 289\u003c\/p\u003e \u003cp\u003eInteroperability with Vertex AI 289\u003c\/p\u003e \u003cp\u003eAccess BigQuery Public Dataset 289\u003c\/p\u003e \u003cp\u003eImport BigQuery Data into Vertex AI 290\u003c\/p\u003e \u003cp\u003eAccess BigQuery Data from Vertex AI Workbench Notebooks 290\u003c\/p\u003e \u003cp\u003eAnalyze Test Prediction Data in BigQuery 290\u003c\/p\u003e \u003cp\u003eExport Vertex AI Batch Prediction Results 290\u003c\/p\u003e \u003cp\u003eExport BigQuery Models into Vertex AI 291\u003c\/p\u003e \u003cp\u003eBigQuery Design Patterns 291\u003c\/p\u003e \u003cp\u003eHashed Feature 291\u003c\/p\u003e \u003cp\u003eTransforms 291\u003c\/p\u003e \u003cp\u003eSummary 292\u003c\/p\u003e \u003cp\u003eExam Essentials 293\u003c\/p\u003e \u003cp\u003eReview Questions 294\u003c\/p\u003e \u003cp\u003e\u003cb\u003eAppendix Answers to Review Questions 299\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eChapter 1: Framing ML Problems 300\u003c\/p\u003e \u003cp\u003eChapter 2: Exploring Data and Building Data Pipelines 301\u003c\/p\u003e \u003cp\u003eChapter 3: Feature Engineering 302\u003c\/p\u003e \u003cp\u003eChapter 4: Choosing the Right ML Infrastructure 302\u003c\/p\u003e \u003cp\u003eChapter 5: Architecting ML Solutions 304\u003c\/p\u003e \u003cp\u003eChapter 6: Building Secure ML Pipelines 305\u003c\/p\u003e \u003cp\u003eChapter 7: Model Building 306\u003c\/p\u003e \u003cp\u003eChapter 8: Model Training and Hyperparameter Tuning 307\u003c\/p\u003e \u003cp\u003eChapter 9: Model Explainability on Vertex AI 308\u003c\/p\u003e \u003cp\u003eChapter 10: Scaling Models in Production 308\u003c\/p\u003e \u003cp\u003eChapter 11: Designing ML Training Pipelines 309\u003c\/p\u003e \u003cp\u003eChapter 12: Model Monitoring, Tracking, and Auditing Metadata 310\u003c\/p\u003e \u003cp\u003eChapter 13: Maintaining ML Solutions 311\u003c\/p\u003e \u003cp\u003eChapter 14: BigQuery ML 313\u003cbr\u003e\u003cbr\u003e Index 315\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eABOUT THE AUTHORS\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003cb\u003eMONA\u003c\/b\u003e is an AI\/ML specialist in the Google Public Sector. She is the author of \u003ci\u003eNatural Language Processing with AWS AI Services\u003c\/i\u003e and a frequent speaker at cloud computing and machine learning events. She was a Sr. AI\/ML specialist SA at AWS before joining Google. She has 14 Certifications and has created courses for AWS AI\/ML Certification Speciality Exam readiness. She has authored 17 articles on AI\/ML and also co-authored a research paper on CORD-19 Neural Search, which won an award at the AAAI Conference on Artificial Intelligence \u003c\/p\u003e\u003cp\u003e\u003cb\u003ePratap Ramamurthy\u003c\/b\u003e is an AI\/ML Specialist Customer Engineer in Google Cloud. Previously, he worked as a Sr. Principal Solution Architect at H2O.ai and before that was a Partner Solution Architect at AWS. He has authored several research papers and holds 3 patents.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eYour one-stop resource to prepare for the highest-paying IT certification out there\u003c\/b\u003e  \u003c\/p\u003e\u003cp\u003eGoogle Cloud Platform is a fast-growing machine learning platform that is highly in demand for engineers and developers. As a Google-certified Professional Machine Learning Engineer, you’ll have the credential you need to demonstrate your mastery of this hot tech. \u003ci\u003eOfficial Google Cloud Certified Professional Machine Learning Engineer Study Guide\u003c\/i\u003e helps you gain the expertise you need to pass the exam and obtain your certification. This book helps you learn core content on data, feature engineering, model training, and deployment of machine learning models on Google Cloud. You’ll also learn important best practices through real-world scenarios, so you can understand exactly how everything works in practice.  \u003c\/p\u003e\u003cp\u003eThis book’s proven study tools include a pre-book assessment exam, chapters with objective maps and review questions, and additional online practice tests with explanations, glossary, and flash cards. You’ll gain the confidence you need to succeed on exam day. \u003c\/p\u003e\u003cp\u003e\u003cb\u003e\u003ci\u003eOfficial Google Cloud Certified Professional Machine Learning Engineer Study Guide\u003c\/i\u003e helps you:\u003c\/b\u003e \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003eFrame machine learning problems\u003c\/li\u003e \u003cli\u003eArchitect machine learning solutions\u003c\/li\u003e \u003cli\u003eDesign data preparation and processing systems\u003c\/li\u003e \u003cli\u003eDevelop, train, and scale machine learning models\u003c\/li\u003e \u003cli\u003eAutomate and orchestrate machine learning pipelines\u003c\/li\u003e \u003cli\u003eMonitor, optimize, and maintain machine learning solutions\u003c\/li\u003e\n\u003c\/ul\u003e \u003cp\u003e\u003cb\u003eInteractive learning environment\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eTake your exam prep to the next level with Sybex’s superior interactive online study tools. To access our learning environment, simply visit \u003cb\u003ewww.wiley.com\/go\/sybextestprep\u003c\/b\u003e, register your book to receive your unique PIN, and instantly gain one year of FREE access to: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eInteractive test bank with 2 practice exams.\u003c\/b\u003e Practice exams help you identify areas where further review is needed. Get more than 90% of the answers correct, and you’re ready to take the certification exam. More than 300 online questions total!\u003c\/li\u003e \u003cli\u003e\n\u003cb\u003eMore than 200 electronic flashcards\u003c\/b\u003e to reinforce learning and last-minute prep before the exam\u003c\/li\u003e \u003cli\u003e\n\u003cb\u003eComprehensive glossary in PDF format\u003c\/b\u003e gives you instant access to the key terms so you are fully prepared\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989710356709,"sku":"NP9781119944461","price":65.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119944461.jpg?v=1761785200","url":"https:\/\/k12savings.com\/products\/official-google-cloud-certified-professional-machine-learning-engineer-study-guide-isbn-9781119944461","provider":"K12savings","version":"1.0","type":"link"}