Summary

In this chapter, we got our feet wet by performing multiple AutoML experiments using a variety of services, capabilities, and tools on AWS. This included using AutoGluon within a Cloud9 environment and SageMaker Canvas and SageMaker Autopilot to run AutoML experiments. The solutions presented in this chapter helped us have a better understanding of the fundamental ML and ML engineering concepts as well. We were able to see some of the steps in the ML process in action, such as EDA, train-test split, model training, evaluation, and prediction.

In the next chapter, we will focus on how the AWS Deep Learning AMIs help speed up the ML experimentation process. We will also take a closer look at how AWS pricing works for EC2 instances so that we are better equipped when managing the overall cost of running ML workloads in the cloud.