02. What's Ahead?

What's Ahead?

In this lesson, you're going to get familiar with what's meant by machine learning deployment. Then in the upcoming lessons, you will put these ideas to practice by using Amazon's SageMaker. SageMaker is just one method for deploying machine learning models.

Specifically in this lesson, we will look at answering the following questions:

1. What's the machine learning workflow?
   
   
2. How does deployment fit into the machine learning workflow?
   
   
3. What is cloud computing?
   
   
4. Why would we use cloud computing for deploying machine learning models?
   
   
5. Why isn't deployment a part of many machine learning curriculums?
   
   
6. What does it mean for a model to be deployed?
   
   
7. What are the essential characteristics associated with the code of deployed models?
   
   
8. What are different cloud computing platforms we might use to deploy our machine learning models?

At the end of this lesson, you'll understand the broader idea of machine learning deployment. Then Sean will be guiding you through using SageMaker to deploy your own machine learning models. This is a lot to cover, but by the end you will have a general idea of all the concepts related to deploying machine learning models into real world production systems.