Take advantage of the power of cloud and the latest AI techniques. Whether you're an experienced developer wanting to improve your app with AI-powered features or you want to make a business process smarter by getting AI to do some of the work, this book's got you covered. Authors Anand Raman, Chris Hoder, Simon Bisson, and Mary Branscombe show you how to build practical intelligent applications for the cloud, mobile, browsers, and edge devices using a hands-on approach.

This book shows you how cloud AI services fit in alongside familiar software development approaches, walks you through key Microsoft AI services, and provides real-world examples of AI-oriented architectures that integrate different Azure AI services. All you need to get started is a working knowledge of basic cloud concepts.

• Become familiar with Azure AI offerings and capabilities
• Build intelligent applications using Azure Cognitive Services
• Train, tune, and deploy models with Azure Machine Learning, PyTorch, and the Open Neural Network Exchange (ONNX)
• Learn to solve business problems using AI in the Power Platform
• Use transfer learning to train vision, speech, and language models in minutes

Table of Contents

Part I. Understanding AI-Oriented Architecture

Chapter 1. An Introduction to Al-Oriented Architecture

Part II. Tools and Services to Help You Build AI-Oriented Architectures

Chapter 2. Understanding Al Offerings and Capabilities

Chapter 3. Train, Tune, and Deploy Models with Azure Machine Learning, ONNX, and PyTorch

Chapter 4. Using Azure Cognitive Services to Build Intelligent Applications

Chapter 5. Using Azure Applied Al Services for Common Scenarios

Chapter 6. Machine Learning for Everyone: Low-Code and No-Code Experiences

Chapter 7. Responsible Al Development and Use

Chapter 8. Best Practices for Machine Learning Projects

Part III. AI-Oriented Architectures in the Real World

Chapter 9. How Microsoft Runs Cognitive Services for Millions of Users

Chapter 10. Seeing Al: Using Azure Machine Learning and Cognitive Services in a Mobile App at Scale

Chapter 11. Translating Multiple Languages at Scale for International Organizations

Chapter 12. Bringing Reinforcement Learning from the Lab to the Convenience Store

Who This Book Is For

The cloud AI services Azure provides bring a wide range of the latest developments to any developer and even to business users, as well as data scientists and data engineers.

There are so many techniques and so many places you might want to use AI that even organizations who are hiring and training data engineers and data scientists want to make them more productive by using AI cloud services. Cloud services also unlock the possibilities of AI for developers and business experts who will never be data engineers or data scientists.

There are so many different AI tools and services from Microsoft that run on Azure that we can’t cover them all in depth, so we’ve picked out four key areas. The Power Platform helps business users and professional developers alike build apps and workflows that take advantage of AI. Azure Cognitive Services and Applied AI Services give developers APIs, software development kits (SDKs), and ready-made solutions to incorporate in their code. Azure Machine Learning is powerful enough for data scientists but also has options that help people who aren’t AI experts to train their own models to solve their particular business problems.

The worlds of AI and cloud services are both fast moving, so what we can capture in this book is the principles behind them, the best practices that will make you successful, and examples of what you can achieve. In particular, we look at how to use AI responsibly: a question of increasing importance for many developers.

We cover the practical, hands-on side of using some key features across the range of services, but bear in mind that those services may have been updated by the time you come to use them. The steps we describe might be slightly different from what you see in the cloud services, performance may have improved, and you will likely find extra features that let you achieve even more!

About the Author

Simon Bisson is a freelance writer, specializing in enterprise technologies and development. He writes for several publications, including InfoWorld, ZDNet, and Computerworld.

Mary Branscombe has worked as a freelance technology journalist for many publications over three decades. Recently she's specialized in AI, enterprise technology, and development.

Chris Hoder is a Program Manager on the Cognitive Services team at Microsoft. Chris focuses on the end-to-end developer experience across the entire suite of services -- from our API and SDK designs to the getting started documentation. In prior roles, Chris worked directly with customers to envision, design, build and deploy AI-focused applications using Microsoft's AI stack.

Anand Raman leads the program management for AI Services Platform at Microsoft. Previously, he was the chief of staff for the Microsoft Azure AI and Data Group, covering data platforms and machine learning, and ran the company's product management and the development teams for Azure Data Services and the Visual Studio and Windows Server user experience teams; he also worked several years as researcher before joining Microsoft. Anand holds a PhD in computational fluid mechanics.