From the course: Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Deployment

Deployment - Azure Tutorial

From the course: Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications

Start my 1-month free trial

Deployment

“

- So deploying your machine learning based system into production should be either the easiest thing you do or the hardest thing you do, depending on how much good prep has been done to reach this stage. So ultimately, we're pushing versions out, in as much as we can, in near real time. So, in other words, we're continuously improving the machine learning based system. So as we're revving the software, doing bug fixes, repairing issues with the knowledge base, repairing the schema, for instance like that, we're always pushing new versions of the data and new versions of the model out to production. We're also doing this in a larger batch format. Now keep in mind that in many instances we may have a dozen to a hundred systems that are all built and staged, and we may want to deploy them through some sort of a batch technology. That may run at midnight when everybody's logged off. And doing that has obvious advantages…

Contents