You're reading from Mastering Azure Machine Learning Perform large-scale end-to-end advanced machine learning in the cloud with Microsoft Azure Machine Learning

Product type Paperback

Published in Apr 2020

Publisher Packt

ISBN-13 9781789807554

Length 436 pages

Edition 1st Edition

Languages

Tools

Azure

Concepts

Machine Learning

Authors (2):

Christoph Körner

Kaijisse Waaijer

View More author details

Table of Contents (20) Chapters

Preface

About Mastering Azure Machine Learning

Section 1: Azure Machine Learning

1. Building an end-to-end machine learning pipeline in Azure FREE CHAPTER

2. Choosing a machine learning service in Azure

Section 2: Experimentation and Data Preparation

3. Data experimentation and visualization using Azure

4. ETL, data preparation, and feature extraction

5. Azure Machine Learning pipelines

6. Advanced feature extraction with NLP

Section 3: Training Machine Learning Models

7. Building ML models using Azure Machine Learning

8. Training deep neural networks on Azure

9. Hyperparameter tuning and Automated Machine Learning

10. Distributed machine learning on Azure

11. Building a recommendation engine in Azure

Section 4: Optimization and Deployment of Machine Learning Models

12. Deploying and operating machine learning models

13. MLOps—DevOps for machine learning

14. What's next?

Index

Summary

In this chapter, we learned the differences between multiple ML and AI services in Azure. You can now easily navigate through various Azure services and know which ML task requires which service. If your task and data is available for Cognitive Services, then it is very convenient to simply use the Cognitive Services API for prediction. This is the case for common computer vision tasks, such as object detection of common objects, image captioning and tagging, face detection, handwritten text recognition, landmark detection, and many other text and language tasks.

If you need to build custom models for data from custom domains, you can choose to pick a tool with a GUI such as Azure Machine Learning designer. However, if you don't know how to select and configure a good custom ML model, Automated Machine Learning would be a better choice for you.

Finally, if you want to create your own custom model, your best choice is the Azure Machine Learning. It is a great tool...