Building Intelligent Cloud Applications

Chapter 5. Using Machine Learning and Deep Learning Models

In this chapter, we examine the use of machine learning models in the cloud. First, we talk about prebuilt and pretrained machine learning services on Azure that we can deploy in a serverless environment. You need no machine learning knowledge to do this.

Then, we explore general machine learning tools such as Jupyter Notebook as well as widely used libraries such as Microsoft Cognitive Toolkit, ML.NET, TensorFlow, scikit-learn, and Keras. This chapter includes brief descriptions of these elements, using terminology that can be difficult to grasp for those without prior knowledge of machine learning.

Last but not least, we talk specifically about cloud machine learning and deep learning services available from Microsoft and show you how to use them in your applications. In this section, you will gain insight into tools like Machine Learning Studio as well as more powerful and sophisticated offerings like Azure Machine Learning Service.

Azure Cognitive Services

The Azure Portal offers several resources that are grouped in what is known as Cognitive Services, which enable you to add machine learning algorithms to your apps, web pages, and bots that in turn empower users to see, hear, speak, understand, and interpret user needs through natural methods of communication. These resources include prebuilt machine learning and deep learning modules that help with the following:

• Recognizing faces

• Sentiment analysis

• Content ...