Azure AI Services at Scale for Cloud, Mobile, and Edge

Table of contents

1. Preface
   1. Who This Book Is For
   2. How to Use This Book
   3. Conventions Used in This Book
   4. Using Code Examples
   5. O’Reilly Online Learning
   6. How to Contact Us
   7. Acknowledgments
2. I. Understanding AI-Oriented Architecture
3. 1. An Introduction to AI-Oriented Architecture
   1. What You Can Do with AI
   2. From Milestones to Models to Architectures
   3. Ready to Jump In?
4. II. Tools and Services to Help You Build AI-Oriented Architectures
5. 2. Understanding AI Offerings and Capabilities
   1. AI Services for All Types of Users
   2. Microsoft’s AI Offerings
      1. Managed AI Services and Infrastructure Options in Azure
      2. Business Platforms with Extensible AI
      3. AI for Big Data and Relational Data
      4. Making Machine Learning More Portable
      5. Cognitive Services
      6. How to Determine What Tool Is Best for You
6. 3. Train, Tune, and Deploy Models with Azure Machine Learning, ONNX, and PyTorch
   1. Understanding Azure Machine Learning
   2. Understanding Azure Machine Learning Studio
   3. Getting Started with Azure Machine Learning
      1. Setting Up a Machine Learning Environment
      2. Integration with Azure Services
   4. Using Visual Studio Code
   5. The Azure Machine Learning Python SDK for Local Development
   6. Azure Machine Learning and R
   7. Build Your First Model Using Azure Machine Learning Studio
      1. Use Automated Machine Learning
      2. Using Designer
      3. Using Azure Machine Learning with Notebooks and Python
   8. Working with Azure Machine Learning Using Different Machine Learning Frameworks
   9. An Introduction to MLOps
      1. Logging in Azure Machine Learning
      2. Tuning Using Hyperparameters
   10. Exporting with ONNX
       1. Using ONNX with WinML
       2. Using ONNX in Machine Learning Container Runtimes
   11. Wrapping It Up
7. 4. Using Azure Cognitive Services to Build Intelligent Applications
   1. Using Prebuilt AI
   2. The Core Azure Cognitive Services
      1. Language
      2. Azure OpenAI Service
      3. Speech
      4. Vision
      5. Decision Making
   3. Wrapping It Up
8. 5. Using Azure Applied AI Services for Common Scenarios
   1. Azure Applied AI Services
      1. Azure Video Analyzer
      2. Cognitive Search
      3. Azure Form Recognizer
      4. Azure Bot Service
      5. Immersive Reader
   2. Use Transfer Learning to Train Vision, Speech, and Language Models in Minutes
      1. Creating a Custom Vision Model
      2. Creating a Custom Speech Model
   3. Wrapping It Up
9. 6. Machine Learning for Everyone: Low-Code and No-Code Experiences
   1. The Microsoft Power Platform
   2. Power BI and AI
      1. AI Visualizations in Power BI
      2. Using AI for Data Preparation in Power BI
      3. Working with Custom Machine Learning Models in Power BI
      4. Building Your Own Custom Models in Power BI
   3. AI Builder
      1. Training a Custom Form Processing Model
      2. Using AI Builder Models
      3. Using Cognitive Services and Other AI Models in Power Automate
      4. Logic Apps and AI
   4. Wrapping It Up
10. 7. Responsible AI Development and Use
    1. Understanding Responsible AI
       1. Responsible AI Improves Performance and Outcomes
       2. Experiment and Iterate
    2. Tools for Delivering Responsible AI
       1. Tools for Transparency
       2. Tools for AI Fairness
       3. Tools for Reliability and Understanding Error
       4. Human in the Loop Oversight
    3. Wrapping It Up
    4. Further Resources
11. 8. Best Practices for Machine Learning Projects
    1. Working Well with Data
       1. Sharing Data
       2. Data Provenance and Governance
    2. Making Machine Learning Projects Successful
       1. Preparing Your Dataset
       2. Establish Performance Metrics
       3. Transparency and Trust
       4. Experiment, Update, and Move On
       5. Collaboration, Not Silos
    3. Wrapping It Up
12. III. AI-Oriented Architectures in the Real World
13. 9. How Microsoft Runs Cognitive Services for Millions of Users
    1. AI for Anyone
    2. Clusters and Containers
14. 10. Seeing AI: Using Azure Machine Learning and Cognitive Services in a Mobile App at Scale
    1. Custom and Cloud Models
    2. The Seeing AI Backend
    3. Getting the Interface Right
15. 11. Translating Multiple Languages at Scale for International Organizations
    1. Delivering Translations for an International Parliament
    2. Connecting to Existing Audio-Visual (AV) Systems
    3. Using Custom Speech Recognition for Specialized Vocabularies
    4. From Specialized Prototype to General Application
    5. Working within Constraints
16. 12. Bringing Reinforcement Learning from the Lab to the Convenience Store
    1. Two APIs, Eight Weeks, 100% Uplift
17. Afterword
18. Index
19. About the Authors