Quantum Causal AI

Learn how causes work, then learn how quantum physics changes the question.¶

You can start this course with no background at all. The first lessons count objects and run fair tests. Later lessons build probability, causal graphs, linear algebra, and quantum information, one checked step at a time. The last levels reach current research on quantum causal models, indefinite causal order, and quantum machine learning.

80 lessons · 8 levels · 11 interactive labs · every source checked

Start at Level 0 · Open the learning map · How to use this book

import sys, pathlib, subprocess
here = pathlib.Path.cwd()
root = next((p for p in [here, *here.parents] if (p / "qcai").is_dir()), None)
if root is None:  # for example on Google Colab: fetch the course's small teaching package
    root = pathlib.Path("quantum-causal-ai")
    if not root.exists():
        subprocess.run(["git", "clone", "--depth", "1", "https://github.com/pozapas/quantum-causal-ai.git", str(root)], check=True)
    root = root.resolve()
sys.path.insert(0, str(root))

Choose a level¶

Each level is a teaching guide, not a certificate. Open a level and try two of its exercises. If they feel easy, move up.

Level 0 · Notice, count, and ask

Grades 1-3 · 10 lessons

Start with objects, light, choices, and fair tests.

Level 1 · Chance, waves, and fair tests

Grades 4-6 · 10 lessons

Use fractions and repeated tests to describe uncertain results.

Level 2 · Algebra, evidence, and causal maps

Grades 7-9 · 10 lessons

Turn verbal questions into variables and models.

Level 3 · Mathematical tools for models

High-school bridge · 10 lessons

Build the mathematical tools that causal and quantum models use.

Level 4 · Classical causal AI

Undergraduate · 10 lessons

Use causal models to define the effect of an action.

Level 5 · Quantum information

Advanced undergraduate · 10 lessons

Build the state, channel, and measurement tools needed for quantum causal models.

Level 6 · Quantum causal models

Graduate · 10 lessons

Connect operational quantum theory with causal questions, explicit assumptions, and testable model classes.

Level 7 · Quantum Causal AI research

Doctoral and postdoctoral · 10 lessons

Define research tasks, audit learning claims, count resources, and build reproducible causal experiments.

What you get¶

Run the science

Each lab is a Jupyter notebook with figures you can drag, rotate, and replay in the browser. You can also download it and run it yourself. Unit tests check the simulation code against exact formulas.

Check every source

A script matched each reference against arXiv, Crossref, or the publisher’s page before it was cited. The full list is in the bibliography.

Read the core textbook

For causal AI, the course follows Elias Bareinboim’s Causal Artificial Intelligence Bareinboim, 2025. Lessons in Levels 2, 4, and 7 point to the matching chapter of the free draft at causalai-book.net.

Watch and listen

Lectures, explainers, and podcast episodes for every level. Each title and channel was fetched from the source itself. See Watch and listen.

References¶

Bareinboim, E. (2025). Causal Artificial Intelligence: A Roadmap for Building Causally Intelligent Systems. https://causalai-book.net/