Chapter 1 of 5 · AWS AIF-C01
Fundamentals of AI and ML
Core terms, learning types, use cases, AWS AI services, the ML lifecycle, metrics and SageMaker AI.
- 8topics
- 33 minfast track
- 2diagrams and exhibits
- 20%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1AI, ML and Deep LearningLearn how artificial intelligence, machine learning, deep learning and generative AI nest inside each other, and the core terms…4 min
- 2Learning Types and Data TypesCompare supervised, unsupervised and reinforcement learning, and the data types that feed them: labeled, unlabeled, structured…4 min
- 3Model Fit, Bias and InferenceUnderstand overfitting, underfitting, bias and variance in models, plus batch versus real time inference and the main ways to…5 min
- 4When to Use AI and MLDecide when AI and ML add value and when simple rules are better, and match business problems to the right ML technique and…4 min
- 5AWS Managed AI ServicesMatch business needs to AWS managed AI services such as Rekognition, Comprehend, Textract, Transcribe, Polly, Translate, Lex…4 min
- 6The ML Development LifecycleWalk through the machine learning lifecycle from business goal and data preparation to training, evaluation, deployment…Diagram4 min
- 7Model Performance MetricsRead the confusion matrix and choose between accuracy, precision, recall, F1 score, AUC and error metrics, and link model scores…4 min
- 8SageMaker AI and MLOpsSee how Amazon SageMaker AI supports each ML lifecycle stage, and how MLOps makes model building repeatable, monitored and ready…Diagram4 min
About this chapter
What this chapter covers
This chapter builds the base for the whole AWS Certified AI Practitioner exam. It explains what AI and machine learning (ML) are, when they are worth using, and how an ML solution is built and run.
It follows the first domain of the AIF-C01 outline, which has three topics.
The first covers basic concepts and terms. The second covers practical use cases, including the AWS managed AI services. The third covers the ML development lifecycle.
The later chapters on generative AI (GenAI) build directly on these ideas, so read this one first.
How the topics fit together
The pages move from vocabulary, to choosing a solution, to building and running it.
- Concepts give you the words used in every later question: model, training, inference, labels, overfitting.
- Use cases teach you to decide if AI is the right tool and which AWS service matches the need.
- The lifecycle shows the stages from business goal to monitoring.
- Metrics and tools show how a model is judged and how SageMaker AI and MLOps keep it running.
Many questions in this chapter are scenario matches. Read the input and the wanted output first, then pick the technique or service that links them.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with diagrams and tables.
- What to remember for the exam: the facts to memorise.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
This is a concepts exam, so focus on definitions, comparisons and the reason one option beats another. You do not need to write code.
Ready for more practice?
The full AWS AIF-C01 question bank has 849 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by AWS. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.