I recently passed my AWS Machine Learning exam! Many thanks to my employer for covering the cost of the exam and some of my training materials. A mentor at my job suggested that I take it because many data science roles in the healthcare space use AWS. You don’t need the exam to find a health data science role, but you probably will use some of the AWS services at work at some point. So, this post is just a brief account of how I passed the exam and will share some resources. I know we have some early career subscribers. Sorry for this post if you are a whiz at AWS already. Subscribe if you are interested in more detailed posts about health data science. If you are already subscribed, thank you so much!
My job paid for this course. I mainly reviewed the sections on MLOps and Modeling since this exam covers models I haven’t had to use yet for work. I felt like this course was a good starting point for preparing for the exam.
I paid for this course. It was on sale for $14.83 when I bought it. This course goes overboard with preparing for the exam, which I appreciated. It covered Deep Learning which I didn’t know much about good enough to pass the exam. I spent most of my time reviewing the different algorithms, security concepts, and the data engineering section.
I spent a lot of time in the AWS documentation for SageMaker. I found this helpful for learning the different hyperparameters for the various algorithms used in SageMaker.
The AWS glossary was great for quickly getting definitions of services. If I missed a question on a practice exam, I would quickly look up a definition for some of the terms here, so I didn’t need to search through the courses.
I took all of these exams. I got them on sale together for $21. If I got something wrong, I added the question to my Anki deck and the correct answer. Eventually, I reviewed all the questions I got wrong in Anki at least 3-to-4 times before the exam.