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.

Building and deploying ML models for production use

Building and deploying ML models for production use

From the course: Deploying Scalable Machine Learning for Data Science

Start my 1-month free trial

Building and deploying ML models for production use

“

- [Instructor] When building models, we focus on data, algorithms, and evaluating performance of models. When we have built our models and we wanna use them in production, at that point we have to shift our focus to more software engineering and DevOps kinds of concerns. Let's take a look at some of those. There's several things we wanna consider as we move from development to production with our machine learning models. We have to think about how we're going to deploy code to our production servers. We also have to realize that our models need to be continuously available. We can't have them down for long periods of time. We also wanna understand that it's not just us, the data scientist, who is working with a model. It may not even be a human being. It could be another application that is making a call to our model, so we wanna make sure that we have easy access from other programs, and typically we do this by using an application programming interface, or API. Now, we don't want it…

Contents