Automated Machine Learning

Automated Machine Learning

by Adnan Masood
Released February 2021
Publisher(s): Packt Publishing
ISBN: 9781800567689

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Get to grips with automated machine learning and adopt a hands-on approach to AutoML implementation and associated methodologies

Key Features

  • Get up to speed with AutoML using OSS, Azure, AWS, GCP, or any platform of your choice
  • Eliminate mundane tasks in data engineering and reduce human errors in machine learning models
  • Find out how you can make machine learning accessible for all users to promote decentralized processes

Book Description

Every machine learning engineer deals with systems that have hyperparameters, and the most basic task in automated machine learning (AutoML) is to automatically set these hyperparameters to optimize performance. The latest deep neural networks have a wide range of hyperparameters for their architecture, regularization, and optimization, which can be customized effectively to save time and effort.

This book reviews the underlying techniques of automated feature engineering, model and hyperparameter tuning, gradient-based approaches, and much more. You'll discover different ways of implementing these techniques in open source tools and then learn to use enterprise tools for implementing AutoML in three major cloud service providers: Microsoft Azure, Amazon Web Services (AWS), and Google Cloud Platform. As you progress, you’ll explore the features of cloud AutoML platforms by building machine learning models using AutoML. The book will also show you how to develop accurate models by automating time-consuming and repetitive tasks in the machine learning development lifecycle.

By the end of this machine learning book, you’ll be able to build and deploy AutoML models that are not only accurate, but also increase productivity, allow interoperability, and minimize feature engineering tasks.

What you will learn

  • Explore AutoML fundamentals, underlying methods, and techniques
  • Assess AutoML aspects such as algorithm selection, auto featurization, and hyperparameter tuning in an applied scenario
  • Find out the difference between cloud and operations support systems (OSS)
  • Implement AutoML in enterprise cloud to deploy ML models and pipelines
  • Build explainable AutoML pipelines with transparency
  • Understand automated feature engineering and time series forecasting
  • Automate data science modeling tasks to implement ML solutions easily and focus on more complex problems

Who this book is for

Citizen data scientists, machine learning developers, artificial intelligence enthusiasts, or anyone looking to automatically build machine learning models using the features offered by open source tools, Microsoft Azure Machine Learning, AWS, and Google Cloud Platform will find this book useful. Beginner-level knowledge of building ML models is required to get the best out of this book. Prior experience in using Enterprise cloud is beneficial.

Table of contents

  1. Automated Machine Learning
  2. Foreword
  3. Contributors
  4. About the author
  5. About the reviewer
  6. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
    4. Download the color images
    5. Conventions used
    6. Get in touch
    7. Reviews
  7. Section 1: Introduction to Automated Machine Learning
  8. Chapter 1: A Lap around Automated Machine Learning
    1. The ML development life cycle
    2. Automated ML
    3. How automated ML works
      1. Hyperparameters
      2. The need for automated ML
    4. Democratization of data science
    5. Debunking automated ML myths
      1. Myth #1 – The end of data scientists
      2. Myth #2 – Automated ML can only solve toy problems
    6. Automated ML ecosystem
    7. Open source platforms and tools
      1. Microsoft NNI
      2. auto-sklearn
      3. Auto-Weka
      4. Auto-Keras
      5. TPOT
      6. Ludwig – a code-free AutoML toolbox
      7. AutoGluon – an AutoML toolkit for deep learning
      8. Featuretools
      9. H2O AutoML
    8. Commercial tools and platforms
      1. DataRobot
      2. Google Cloud AutoML
      3. Amazon SageMaker Autopilot
      4. Azure Automated ML
      5. H2O Driverless AI
      6. The future of automated ML
      7. The automated ML challenges and limitations
      8. A Getting Started guide for enterprises
    9. Summary
    10. Further reading
  9. Chapter 2: Automated Machine Learning, Algorithms, and Techniques
    1. Automated ML – Opening the hood
      1. The taxonomy of automated ML terms
    2. Automated feature engineering
    3. Hyperparameter optimization
    4. Neural architecture search
    5. Summary
    6. Further reading
  10. Chapter 3: Automated Machine Learning with Open Source Tools and Libraries
    1. Technical requirements
    2. The open source ecosystem for AutoML
    3. Introducing TPOT
      1. How does TPOT do this?
    4. Introducing Featuretools
    5. Introducing Microsoft NNI
    6. Introducing auto-sklearn
    7. AutoKeras
      1. Ludwig – a code-free AutoML toolbox
    8. AutoGluon – the AutoML toolkit for deep learning
    9. Summary
    10. Further reading
  11. Section 2: AutoML with Cloud Platforms
  12. Chapter 4: Getting Started with Azure Machine Learning
    1. Getting started with Azure Machine Learning
    2. The Azure Machine Learning stack
    3. Getting started with the Azure Machine Learning service
    4. Modeling with Azure Machine Learning
    5. Deploying and testing models with Azure Machine Learning
    6. Summary
    7. Further reading
  13. Chapter 5: Automated Machine Learning with Microsoft Azure
    1. AutoML in Microsoft Azure
    2. Time series prediction using AutoML
    3. Summary
    4. Further reading
  14. Chapter 6: Machine Learning with AWS
    1. ML in the AWS landscape
    2. Getting started with AWS ML
    3. AWS SageMaker Autopilot
    4. AWS JumpStart
    5. Summary
    6. Further reading
  15. Chapter 7: Doing Automated Machine Learning with Amazon SageMaker Autopilot
    1. Technical requirements
    2. Creating an Amazon SageMaker Autopilot limited experiment
    3. Creating an AutoML experiment
    4. Running the SageMaker Autopilot experiment and deploying the model
      1. Invoking the model
    5. Building and running SageMaker Autopilot experiments from the notebook
      1. Hosting and invoking the model
    6. Summary
    7. Further reading
  16. Chapter 8: Machine Learning with Google Cloud Platform
    1. Getting started with the Google Cloud Platform services
    2. AI and ML with GCP
    3. Google Cloud AI Platform and AI Hub
    4. Getting started with Google Cloud AI Platform
    5. Automated ML with Google Cloud
    6. Summary
    7. Further reading
  17. Chapter 9: Automated Machine Learning with GCP
    1. Getting started with Google Cloud AutoML Tables
    2. Creating an AutoML Tables experiment
    3. Understanding AutoML Tables model deployment
    4. AutoML Tables with BigQuery public datasets
    5. Automated machine learning for price prediction
    6. Summary
    7. Further reading
  18. Section 3: Applied Automated Machine Learning
  19. Chapter 10: AutoML in the Enterprise
    1. Does my organization need automated ML?
      1. Clash of the titans – automated ML versus data scientists
    2. Automated ML – an accelerator for enterprise advanced analytics
      1. The democratization of AI with human-friendly insights
      2. Augmented intelligence
    3. Automated ML challenges and opportunities
      1. Not having enough data
      2. Model performance
      3. Domain expertise and special use cases
      4. Computational costs
      5. Embracing the learning curve
      6. Stakeholder adaption
    4. Establishing trust – model interpretability and transparency in automated ML
      1. Feature importance
      2. Counterfactual analysis
      3. Data science measures for model accuracy
      4. Pre-modeling explainability
      5. During-modeling explainability
      6. Post-modeling explainability
    5. Introducing automated ML in an organization
      1. Brace for impact
      2. Choosing the right automated ML platform
      3. The importance of data
      4. The right messaging for your audience
    6. Call to action – where do I go next?
    7. References and further reading
    8. Why subscribe?
  20. Other Books You May Enjoy
    1. Packt is searching for authors like you
    2. Leave a review - let other readers know what you think

Product information

  • Title: Automated Machine Learning
  • Author(s): Adnan Masood
  • Release date: February 2021
  • Publisher(s): Packt Publishing
  • ISBN: 9781800567689