From the course: Complete Guide to Azure AI for ML Engineers by Microsoft Press
Join today to access over 25,300 courses taught by industry experts.
Learn about performance tuning - Azure Tutorial
From the course: Complete Guide to Azure AI for ML Engineers by Microsoft Press
Learn about performance tuning
- [Instructor] Now that you have your model deployed to production or your user environment, let's talk about the next phase in this lifecycle. And that's where you might do some performance tuning or performance optimization. Over time as your AI solutions sit in production and users constantly interact with them, you'll notice a type of drift that happens over time. And this could be a concept drift, where the solution you have just slowly deviates from the actual problem that users are facing. Or you might run into data drift where the inputs you are getting from your users is different from the data the model was trained on. So these are a couple of things that you should always be monitoring for as your model and your applications sit in this production environment. And also keep an eye out for when new models become available. Typically, new models are going to have some kind of better performance, maybe they have more accurate solutions, whatever it is, keep an eye out for…
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.