AI Foundations›Core· 25 min read

AI vs Machine Learning vs Deep Learning

Three nested circles: deep learning is part of machine learning, which is part of AI.

What you will learn

Place AI, ML and deep learning in the right relationship
Explain deep learning in one sentence
Know when each term applies

Three circles inside each other

These three words get mixed up constantly. They are nested, like Russian dolls:

Artificial Intelligence — the big idea: any software that acts “smart”.
Machine Learning — a part of AI: systems that learn from data (most of modern AI).
Deep Learning — a part of ML: learning with neural networks that have many layers.

AI ⊃ Machine Learning ⊃ Deep Learning

AI  ─ the whole field (smart software)
│
└── Machine Learning  ─ learns patterns from data
    │
    └── Deep Learning  ─ machine learning using deep neural networks

So all deep learning is machine learning, and all machine learning is AI — but not the other way round. A rule-based tax program is AI, but it is not machine learning.

Term	In one line	Example
AI	Software that acts intelligently	A chess engine, a spam filter, ChatGPT
Machine Learning	AI that learns from data	Predicting house prices from past sales
Deep Learning	ML using many-layered neural networks	Recognising faces, understanding speech

Tip: Deep learning powers the headline breakthroughs (image recognition, ChatGPT) because deep neural networks can learn extremely complex patterns — at the cost of needing lots of data and computing power.

Q. Which statement is correct?

Answer: Deep learning is a subset of machine learning, which is a subset of AI. The broader claims are false (e.g. rule-based AI is not ML).

✍️ Practice

Draw the three nested circles and label each with your own example.
Decide: a rule-based chatbot — is it AI? Is it machine learning? Explain.

🏠 Homework

Find a news article using one of these three terms and judge whether it used the word correctly.