From the course: Deploying Scalable Machine Learning for Data Science
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Running models as services
From the course: Deploying Scalable Machine Learning for Data Science
Running models as services
- [Instructor] Now we're going to turn our attention to understanding what exactly do we mean when we talk about running a model as a service? I've been using the term service throughout this course. It's a common term when discussing architecture and distributed computing. But it's worth examining in a little more detail. Services are a software abstraction for describing executing programs that share common characteristics. Now these include that the service or the software is accessible over the network. It can be invoked using standard network protocols, typically HTTP, at least when we're talking about restful services. These services tend to perform a single function, and oftentimes they don't take a long time to run. These are fairly quick running operations. And also they can be deployed in parallel. Services can be distinguished by how they exchange data. For example, restful services often pass data in JSON structures. High-volume services sometimes use other protocols such…
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.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.