Fundamentals of AI and ML

Artificial intelligence, machine learning and deep learning are three nested ideas, not three competing technologies. This lesson defines each one, plus the terms the exam expects you to know alongside them: neural networks, computer vision, natural language processing, models, algorithms…

Generative AI, large language models and agentic AI are the newest layers of the AI family. This lesson explains what each one is, how they fit inside machine learning and deep learning, and what makes a system "agentic" rather than just generative.

Once a model is trained, it earns its keep through inference: making predictions on new data. Amazon SageMaker AI offers four ways to run inference: real-time, serverless, asynchronous and batch. This lesson shows how to pick one from three clues in a scenario: how fast an answer is needed, how…

Every AI model is shaped by the data it learns from, and the kind of data narrows down the kind of model and learning method you can use. This lesson covers the data distinctions the exam names: labeled and unlabeled, structured and unstructured, and the common types: tabular, time-series, image…

Machine learning comes in three main types, and the data you have usually decides which one fits. This lesson explains supervised, unsupervised and reinforcement learning with a typical use for each, then covers three terms the exam pairs with them: fit, bias and fairness.

AI earns its place in a business when it does something people can't do well at the same speed, scale or consistency: spotting patterns in huge amounts of data, handling repetitive work, or personalizing an experience for millions of customers at once. This lesson covers the three kinds of value…

Knowing when not to use AI is as important for the exam as knowing when to use it. Machine learning gives you a prediction, a best guess learned from data, and it costs money to build, run and maintain. If the business needs an exact answer, has little data, or would gain less than it spends, a…

Regression, classification and clustering are the three machine learning techniques the exam expects you to tell apart from a one-line business problem. The trick is to look at the shape of the answer the business wants: a number, a category or a set of groups nobody has named yet. Get that right…

The exam often describes a business situation and expects you to name the kind of AI application behind it. Most real-world uses fall into a small set of families: seeing (computer vision), understanding language (natural language processing), hearing (speech recognition), suggesting…

AWS offers a set of managed AI services, each pre-trained for one specific job, so a business can add speech, language, vision or recommendation features through an API call, without any machine learning expertise. When none of them fits, Amazon SageMaker AI is the platform for building, training…

Not every AI problem needs a foundation model. A foundation model (FM) is a very large model pre-trained on broad data that can handle many tasks, especially generating text, images or code. A traditional ML model is smaller and trained for one narrow job, such as predicting churn or scoring…

A machine learning (ML) pipeline is the series of stages that turns a business problem and raw data into a working model that keeps performing well. The exam expects you to name each stage, say what it produces, and recognise which stage a scenario is describing.

Before a team can use a model, it has to get one. It can use a ready-made model from a provider, start from an open-source pre-trained model, or train its own from scratch. The exam asks you to match each source to a situation, and to know which AWS service offers which kind of model.

Once a model is chosen, applications need a way to send it requests and get answers back. There are two main ways to do that: call a managed API service, where someone else runs the model, or host the model yourself behind your own API. The exam tests the trade-offs between the two: effort…

AWS has a service or feature for almost every stage of the AI and machine learning (ML) pipeline. The exam often describes one stage in a scenario and asks which service fits it. This lesson maps the main services to the stages where they help, from preparing data to watching a deployed model.

Machine learning operations (MLOps) is the set of practices that takes ML from one-off experiments to reliable systems that keep working in production. It borrows ideas from DevOps, such as automation, version control and monitoring, and adds what's special about models: they depend on data, and…

A model can be judged in two ways: how well it predicts, and whether it's worth what it costs. Model performance metrics such as accuracy, precision, recall and F1 score measure the first. Business metrics such as cost per user and return on investment measure the second. The exam asks you to pick…