Probability & Probabilistic Computing Tutorial
A Narrative Introduction to Probability
Probability, probabilistic machine learning, and probabilistic computing β told as one school year in the life of Chibany, the Chiba Tech mascot.
No prior math background required. Every idea arrives scene-first: a concrete bento mystery, then the math it forces, then runnable GenJAX code.
Two ways to read this book
π€ Beginner
Probability theory β probabilistic ML β probabilistic computing, through to neural networks, LLMs, and ML ethics β from a light background.
π§ CogSci
Bayesian cognitive science: probabilistic models as theories of minds β generalization, memory, sampling, goal inference, theory of mind.
New here? Begin with Start Here: How to Read This Book.
The book at a glance
| Part | Chibany’s year | You learn |
|---|---|---|
| I. Foundations | Will there be tonkatsu today? | events, counting, conditioning, Bayes’ rule |
| II. The Tools | teach the laptop to imagine days | GenJAX: simulate, trace, condition, infer |
| III. Continuous Probability & Bayesian Learning | the Mystery of the Two Peaks | densities, Gaussians, Bayesian updating, mixtures |
| IV. Structure | the Bento Provenance Project | generalization, Bayes nets, causality, information, hierarchies |
| V. Chains, Walks & Sampling | the question you can’t sum | Markov chains, random walks, MC, particle filters, MCMC |
| VI. Decisions & RL | Chibany learns to act | decision theory, MDPs, Q-learning, inverse RL, POMDPs |
| VII. Model Complexity | the Winter Model Fair | biasβvariance, Bayesian nonparametrics, Gaussian processes |
| VIII. Deep Networks | the kiosk & the trainee | neural nets, transformers, LLMs & in-context learning |
| IX. Ethics, Fairness & Safety | the Mascot’s Code | adversarial ML, fairness, bias, alignment |
Also on the site: the Glossary, the Notebook Guide (every chapter’s Colab companion), and Acknowledgements.
This project is generously funded by the Japanese Probabilistic Computing Consortium Association (JPCCA).