From the course: Deploying Scalable Machine Learning for Data Science
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Overview of tools and techniques for scalable ML
From the course: Deploying Scalable Machine Learning for Data Science
Overview of tools and techniques for scalable ML
- [Instructor] Let's take a look at some of the tools and techniques we'll use for scaling our machine learning models. It's clear that running machine learning models on clusters of servers has its advantages when we want to deploy a scalable, highly available system. But how do we deploy our models to these multiple machines, especially when we're adding and removing servers depending on demand? Well, we do this by following a pattern used to deploy microservices. Now, this pattern includes deploying the model with an application programming interface, or API, that makes it easy to access from other services. We run the models and API in a container that includes all the software needed to run the model as well as any supporting services we might need. And finally, we manage the containers in the cluster using an orchestration service. In this course, we'll introduce the tools and platforms for deploying scalable machine learning models using this pattern. We'll discuss how we can…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.