Automated Machine Learning: Hyperparameter optimization, neural architecture search, and algorithm selection with cloud platforms

✍ Scribed by Adnan Masood

• Publisher: Packt Publishing Ltd
• Year: 2021
• Tongue: English
• Leaves: 312
• Category: Library

✦ Synopsis

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

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