Machine Learning Theory and Applications

6Machine Learning in Production

Photo by Annamária Borsos

How many artificial intelligence (AI) models that have been created have been put into production? With investment in data science teams and technologies, the number of AI projects has increased significantly and with it a number of missed opportunities to put them into production and assess their true business value. The goal of this chapter is to provide a brief introduction to several technologies that can help bring our AI models to life.

6.1 Why Use Docker Containers for Machine Learning?

Even though there are different containerization technologies, we will choose Docker to explain why containerization of machine learning applications is important. Docker is an open‐source technology that allows packaging of applications into containers.

6.1.1 First Things First: The Microservices

The first thing to understand before talking about containerization is the concept of microservices. If a large application is broken down into smaller services, each of those services or small processes can be termed microservices, and they communicate with each other over a network. The microservice approach is the opposite of the monolithic approach, which can be difficult to scale. If one particular feature has some issues or crashes, all other features will experience the same. Another example is when the demand for a particular ...