Summary

You are now heading toward the end of this chapter, in which you have learned about several important topics regarding the foundations of ML. You started the chapter with a theoretical discussion about AI, ML, and DL, and how this entire field has grown over the past few years due to the advent of big data platforms, cloud providers, and AI applications.

You then moved on to the differences between supervised, unsupervised, and reinforcement learning, highlighting some use cases related to each of them. This is likely to be a topic in the AWS Machine Learning Specialty exam.

You learned that an ML model is built in many different stages and the algorithm itself is just one part of the modeling process. You also learned about the expected behaviors of a good model.

You did a deep dive into data splitting, where you learned about different approaches to train and validate models, and you became aware of the mythic battle between variance and bias. You completed the chapter by getting a sense of ML frameworks and services.

Coming up next, you will learn about AWS application services for ML, such as Amazon Polly, Amazon Rekognition, Amazon Transcribe, and many other AI-related AWS services. But first, look at some sample questions to give you an idea of what you can expect in the exam.