Course 797:
Google Cloud Advanced Skills & Certification Workshop: Professional Machine Learning Engineer

 

Google Cloud Certification Training Description

This workshop is designed to help IT professionals prepare for the Google Cloud Professional Machine Learning Engineer certification exam. 

A Professional Machine Learning Engineer designs, builds, and productionizes ML models to solve business challenges using Google Cloud technologies and knowledge of proven ML models and techniques. The Professional Cloud ML exam assesses your ability to frame ML problems, architect ML solutions, develop ML models, automate and orchestrate ML pipelines, and more.

In this workshop, we review the exam guidelines and cover the main topics you may be tested on.

Learning Objectives

  • Prepare for the Google Cloud Professional Machine Learning Engineer certification exam
  • Simplify and automate machine learning operations using Google Cloud tools
  • Learn some of the basics of Machine Learning
  • Implement the steps required to build a production ML pipeline
  • Build batch and streaming data pipelines with Google Cloud Dataflow
  • Perform Feature Engineering using Dataflow and BigQuery
  • Train and validate ML models using BigQuery ML, AutoML, and TensorFlow
  • Leverage Vertex AI to manage ML datasets, models, experiments, and deployments
  • Program Vertex AI pipelines using Kubeflow

This workshop includes instructor lecture, demos, exercises, practice exams, and links to recommended study, videos, and tutorials. Homework assignments are also included to help students further prepare for the exam.

Prerequisites

Prior to taking the Professional Machine Learning Engineer certification exam, students must have experience programming, validating, deploying, and troubleshooting ML applications running on Google Cloud. 

This workshop assumes prior knowledge of Google Cloud and is not an introduction. Experience deploying applications on Google Cloud, and some knowledge of data engineering and machine learning is assumed.

Practice Quizzes and Hands-On Exercises

Included with this course are sample quizzes and numerous hands-on exercises that will help you both prepare for the exam and efficiently manage real-world deployments using automated tools.

Course Outline

 

Module 1: Professional ML Engineer Certification Overview 

  • Exam Overview and Expectations
    • What You Are Tested On
    • Exam Format
    • Registering for the Exam
  • Exam Prep
    • Exercise: Creating a Google Cloud Account

Module 2: Machine Learning  

  • ML Basics
    • ML Examples
    • Models
    • Examples
    • Features 
    • Labels
    • Training, Validation, and Test Data
    • Training
    • Validation
    • Hyperparameters
    • Prediction
  • Linear Regression Models
    • Linear Regression
    • Linear Regression Examples
    • Validating Linear Regression Models
    • RMSE
    • Exercise: Building a Linear Regression Model
  • Classification Models
    • Classification
    • Classification Examples
    • Validating Classification Models
    • Accuracy 
    • Precision
    • Recall
    • Area Under Receiver Operator Curve (AUROC)
    • Exercise: Building a Classification Model
  • Neural Networks
    • Neural Networks
    • Example
    • Neurons
    • Layers
    • Weights
    • Exercise: Building a Neural Network

Module 3: MLOps   

  • ML Steps
    • Data Collection
    • Feature Engineering
    • Training
    • Validation
    • Putting Models Into Production
  • ML Pipelines
    • Batch ML Pipelines
    • Online Prediction Models
    • On-device Prediction Models
    • Streaming ML Pipelines

Module 4: Creating Data Pipelines with Dataflow

  • Dataflow Basics
  • Apache Beam
    • Creating a Pipeline
    • Pipeline Basics
    • PCollections
    • Transforms
    • I/O
    • Dataflow Templates
    • Exercise: Programming Apache Beam Pipelines
  • Batch Dataflow Pipelines
    • Dataflow Basics
    • Running Dataflow Jobs
    • Exercise: Running Dataflow Jobs
  • Streaming Dataflow Pipelines
    • Example
    • Exercise: Building a Streaming Pipeline with DataFlow Templates 

Module 5: Feature Engineering

  • Feature Engineering Basics
    • Analyzing Features
    • Discovering Relationships in Data
    • Dealing with Incomplete or Invalid Data
    • One-Hot Encoding
  • Feature Engineering in Dataflow
    • Writing Transforms
    • ParDo
    • Side Inputs
    • Dataflow SQL
    • Exercise: Feature Engineering with Dataflow
  • Feature Engineering with BigQuery
    • Tuning Features with SQL
    • Joins
    • Filters 
    • User-Defined Functions
    • Saving Results to Tables
    • Exporting Tables
    • Exercise: Feature Engineering with BigQuery

Module 6: Training and Validating ML Models on Google Cloud

  • BigQuery ML
    • Training ML Models with SQL
    • Model Types
    • Options
    • Splitting the Data
    • Training
    • Validation
    • Prediction
    • Exercise: Programming Models with BigQueryML
  • AutoML
    • Tables
    • Vision
    • Natural Language
    • Video
    • Creating Datasets
    • Labeling
    • Training
    • Validation
    • Exercise: Using AutoML Vision 

Module 7: Vertex AI 

  • Vertex AI Basics
    • Vertex AI Workflow
    • Using Vertex AI
  • Managing Training Data 
    • Datasets
    • Image Datasets
    • Tabular Datasets
    • Text Datasets
    • Labeling Tasks
  • Managing Models
    • Training 
    • Deploying Models
    • Importing Models from BigQuery ML
    • Exporting Models
    • Endpoints
    • Predictions
    • Batch Predictions
    • Exercise: Creating and Deploying Vertex AI Models
  • Vertex AI Pipelines
    • AI Pipeline Architecture
    • TFX vs.Kubeflow Pipelines
    • Google-Provided Pipeline Components
    • Programming Custom AI Pipeline Components
    • Running and Monitoring AI Pipelines
    • Exercise: Running Vertex AI Pipelines