Topics

• Google Cloud Infrastructure
• Compute Power
• Storage
• Networking
• Security
• Big Data and Machine Learning Products

Objectives

• Identify the different aspects of Google Cloud’s infrastructure
• Identify the big data and ML products that form Google Cloud

Activities

• Explore a customer use case
• Lab 1: Exploring a Public Dataset with BigQuery

Topics

• Recommendation Systems
• Choosing the Right Solution Approach
• On-premise to Google Cloud
• Off-cluster Storage with Google Cloud Storage
• Storing Recommendations

Objectives

• Review how businesses use recommendation models
• Evaluate how and where you will compute and store your housing rental model results
• Analyze how running Hadoop in the cloud with Dataproc can enable scale
• Evaluate different approaches for storing recommendation data off-cluster

Activities

• Lab 2: Recommending Products using Cloud SQL and Spark

Topics

• Introduction to BigQuery
• Insights from Geographic Data
• Machine Learning on Structured Data
• Creating ML Models with SQL
• Key Features Walkthrough

Objectives

• Analyze big data at scale with BigQuery
• Learn how BigQuery processes queries and stores data at scale
• Walkthrough key ML terms: features, labels, training data
• Evaluate the different types of models for structured datasets
• Create custom ML models with BigQuery ML

Activities

• Lab 3: Predicting Visitor Purchases w/BigQuery ML

Topics

• Modern Data Pipeline Challenges
• Message-oriented Architectures
• Serverless Data Pipelines
• Designing Streaming Pipelines With Apache Beam
• Implementing Streaming Pipelines on Dataflow
• Data Visualization With Data Studio
• Tips and Tricks to Create Charts With the Data Studio UI

Objectives

• Identify modern data pipeline challenges and how to solve them at scale with Dataflow
• Design streaming pipelines with Apache Beam
• Build collaborative real-time dashboards with Data Studio

Activities

• Lab 4: Creating a Streaming Data Pipeline for a Real-Time Dashboard with Dataflow

Topics

• ML Drives Business Value
• How Does ML on Unstructured Data Work?
• Choosing the Right ML Approach
• Pre-built AI Building Blocks
• Customizing Pre-built Models with AutoML
• Building a Custom Model

Objectives

• Evaluate how businesses use unstructured ML models and how the models work
• Choose the right approach for machine learning models between pre-built and custom
• Create a high-performing custom image classification model with no code using AutoML

Activities

• Lab 5: Classifying Images of Clouds in the Cloud with AutoML Vision

Topics

• Recap of key learning points
• Resources