Module 1 · What AI Really Is
The Core Vocabulary: AI, ML, DL, and Data Science
50 min
Learning objectives
- Correctly use the terms AI, machine learning, deep learning, and data science
- Describe how these fields nest and overlap
- Define 'model' precisely
How the terms nest
These words are often used interchangeably in the press, but practitioners use them precisely. They nest: deep learning is a kind of machine learning, and machine learning is a kind of artificial intelligence.
- Artificial Intelligence — the whole field of intelligent-seeming systems.
- Machine Learning — the subset that learns from data.
- Deep Learning — the subset of ML using multi-layer neural networks.
- Data Science — overlaps with ML but is broader: statistics, analysis, and communicating insight.
Analogy
Picture nested boxes: a small box (deep learning) inside a medium box (machine learning) inside a large box (AI). Data science is a partly-overlapping box next to them.
What is a “model”?
A model is the trained artifact — a mathematical function with learned parameters that maps inputs (an email, an image) to outputs (spam/not-spam, a label). 'Training' is the process of fitting those parameters to data; 'inference' is using the trained model on new inputs.
Model — A trained function that maps inputs to outputs using parameters learned from data.
Train once (fit parameters to data), then infer many times (apply the model to new inputs).
Knowledge check
Quick practice — not part of your exam score.
Which ordering correctly reflects how these fields nest, from broadest to narrowest?
Sign in to track your progress and mark lessons complete.
Sign in