Start Here: How to Read This Book :: Probability & Probabilistic Computing Tutorial

The Beginner Track: Probability → Probabilistic ML → Probabilistic Computing

Thu, 02 Jul 2026 00:00:00 +0000

For readers starting from a light background who want to end up genuinely fluent in probabilistic machine learning — through neural networks, LLMs, and the ethics of deployed models. Set Beginner as my track The roadmap graph TB A[I. Foundations
counting → Bayes] --> B[II. The Tools
GenJAX] B --> C[III. Continuous Probability
& Bayesian Learning] C --> D[IV. Structure
generalization*, Bayes nets, hierarchies] D --> E[V. Chains, Walks & Sampling
Markov chains, MC, MCMC] E --> F[VI. Decisions & RL
MDPs, Q-learning, POMDPs] F --> G[VII. Model Complexity
bias-variance, DPMM, GPs] G --> H[VIII. Deep Networks
NNs, transformers, LLMs] H --> I[IX. Ethics, Fairness & Safety] style A fill:#1565c0,color:#fff style H fill:#27ae60,color:#fff style I fill:#27ae60,color:#fff Reading order Part I — Foundations: all chapters Part II — The Tools (GenJAX): all chapters Part III — Continuous Probability & Bayesian Learning: all chapters Part IV — Structure: Generalization (the setup and number-game parts are enough — the Shepard and No-Free-Lunch parts are the CogSci deep end), then Bayes nets, conditional independence, causality, information theory, hierarchical Bayes Part V — Chains, Walks & Sampling: Markov chains, random walks, Monte Carlo, particle filtering, MCMC (memory search and Sampling the Mind are CogSci-badged extras) Part VI — Decisions & RL: decision theory, MDPs, Q-learning, POMDPs, modern RL (Inverse RL is a CogSci-badged extra — skim its RLHF section) Part VII — Model Complexity: all chapters — this Part is for you Part VIII — Deep Networks: all chapters Part IX — Ethics, Fairness & Safety: all chapters Off-track chapters are never forbidden — they are dimmed, not hidden. If a 🧠-badged chapter looks interesting, read it.

The CogSci Track: Bayesian Cognitive Science

Thu, 02 Jul 2026 00:00:00 +0000

For readers who want to use probabilistic modeling to build and test theories of minds — human or machine. Set CogSci as my track The roadmap graph TB A[I. Foundations
counting → Bayes] --> B[II. The Tools
GenJAX] B --> C[III. Continuous Probability
& Bayesian Learning] C --> D[IV. Structure — in full
generalization, Shepard, causality] D --> E[V. Chains, Walks & Sampling — in full
memory search, sampling the mind] E --> F[VI. Decisions & RL — in full
inverse RL, theory of mind, POMDPs] F --> G[VII. Model Complexity
the DPMM chapter] G --> H[VIII. Deep Networks
LLMs & in-context learning] H --> I[IX. Ethics
fairness, bias, alignment] style D fill:#27ae60,color:#fff style E fill:#27ae60,color:#fff style F fill:#27ae60,color:#fff Reading order Part I — Foundations: all chapters Part II — The Tools (GenJAX): all chapters Part III — Continuous Probability & Bayesian Learning: all chapters Part IV — Structure, in full — the generalization chapter (all four parts, including Shepard’s law and No Free Lunch) is a centerpiece of this track Part V — Chains, Walks & Sampling, in full — including Memory Search as a Random Walk and Sampling the Mind Part VI — Decisions & RL, in full — including Inverse RL (goal inference and theory of mind), POMDPs, and the modern-RL frontier Part VII — Model Complexity: the Discrete Bayesian Nonparametrics chapter (Anderson’s rational model of categorization lives here); bias-variance and GPs are 🤖-badged extras Part VIII — Deep Networks: LLMs & In-Context Learning (in-context learning as implicit hierarchical Bayes) and World Models Part IX — Ethics, Fairness & Safety: fairness formalisms, bias in data, alignment This project is generously funded by the Japanese Probabilistic Computing Consortium Association (JPCCA).