Machine Learning on Google Cloud

(5 days)

 

Course Description

This five-day course teaches learners best practices to implement machine learning on Google Cloud, how to determine appropriate data preprocessing options, use Vertex AI Feature Store for data management, and build Vertex AI AutoML and BigQuery ML models. Students learn to use feature engineering to improve ML model performance, create Vertex AI custom training jobs, write distributed ML models that scale in TensorFlow, and more!

Objectives

  • Build, train, and deploy an ML model by using Vertex AI AutoML
  • Understand when to use AutoML and BigQuery ML
  • Create Vertex AI-managed datasets
  • Add features to the Vertex AI Feature Store
  • Describe Analytics Hub, Dataplex, and Data Catalog
  • Describe how Vertex AI Vizier is used to improve model performance
  • Create a Vertex AI Workbench user-managed notebook, build a
    custom training job, and then deploy it by using a Docker container
  • Describe batch and online predictions and model monitoring
  • Describe how to improve data quality and explore your data
  • Build and train supervised learning models
  • Optimize and evaluate models by using loss functions and
    performance metrics
  • Create repeatable and scalable train, eval, and test datasets
  • Implement ML models using TensorFlow or Keras
  • Understand the benefits of using feature engineering
  • Explain Vertex AI Model Monitoring and Vertex AI Pipelines

Prerequisites

  • Some familiarity with basic machine learning concepts.
  • Basic proficiency with a scripting language, preferably Python.

Audience

  • Aspiring machine learning data analysts, data scientists and data engineers
  • Learners who want exposure to ML and use Vertex AI AutoML, BigQuery ML, Vertex AI Feature Store, Vertex AI Workbench, Dataflow, Vertex AI Vizier for hyperparameter tuning, TensorFlow/Keras.

Course Outline

 

Module 1: How Google Does Machine Learning

  • Describe the Vertex AI Platform and how it is used to quickly build, train, and deploy AutoML machine learning models without writing a single line of code
  • Describe best practices for implementing machine learning on Google Cloud
  • Develop a data strategy around machine learning
  • Examine use cases that are then reimagined through an ML lens
  • Use theGoogle Cloud platform tools and environment to do ML
  • Learn from Google’s experience to avoid common pitfalls
  • Perform data science tasks in online, collaborative notebooks

Module 2: Launching into Machine Learning

  • Describe how to improve data quality
  • Perform exploratory data analysis
  • Build and train supervised learning models
  • Describe AutoML and how to build, train, and deploy an ML model without writing a single line of code
  • Describe BigQuery ML and its benefits
  • Optimize and evaluate models using loss functions and performance metrics
  • Mitigate common problems that arise in machine learning
  • Create repeatable and scalable training, evaluation, and test datasets.

Module 3: TensorFlow on Google Cloud

  • Create TensorFlow and Keras machine learning models
  • Describe TensorFlow key components
  • Use the tf.data library to manipulate data and large datasets
  • Build a ML model using tf.keras preprocessing layers
  • Use the Keras Sequential and Functional APIs for simple and advanced model creation
  • Train, deploy, and productionalize ML models at scale with the Vertex AI Training Service

Module 4: Feature Engineering

  • Describe Vertex AI Feature Store
  • Compare the key required aspects of a good feature
  • Use tf.keras.preprocessing utilities for working with image data, text data, and sequence data
  • Perform feature engineering using BigQuery ML, Keras, and TensorFlow

Module 5: Machine Learning in the Enterprise

  • Understand the tools required for data management and governance
  • Describe the best approach for data preprocessing: from providing an overview of Dataflow and Dataprep to using SQL for preprocessing tasks
  • Explain how AutoML, BigQuery ML, and custom training differ and when to use a particular framework
  • Describe hyperparameter tuning using Vertex AI Vizier to improve model performance
  • Explain prediction and model monitoring and how Vertex AI can be used to manage ML models
  • Describe the benefits of Vertex AI Pipelines
  • Describe best practices for model deployment and serving, model monitoring, Vertex AI Pipelines, and artifact organization