The AI & Machine Learning Encyclopedia

A comprehensive, plain-English reference for the whole field of artificial intelligence and machine learning — every major topic explained as an intuition-first, example-rich guide with interactive demos and visualizations.

A complete, plain-English reference for the entire field of AI and machine learning — from the mathematics underneath it, through classical ML, deep learning, reinforcement learning, and the language/vision/multimodal frontier, to classical symbolic AI, applied systems, and the production, ethics, and research directions shaping what comes next. 47 chapters across 14 parts.

Read it as one continuous story. The chapters form a single arc — each one ends by handing off to the next (look for the ↪ The thread continues note at the foot of every page), so you can read straight through from the mathematics to a deployed, self-improving system, or dip into any chapter on its own.

Every chapter is a clear, intuition-first explainer — flowing guide-style prose that builds each idea step by step, with a diagram, formula, snippet of code, or small visual wherever it makes the concept click. (If you want interview-style question-and-answer drills instead, see the Interview Handbook.)

How to use this: each chapter is its own fast-loading page. Read one top to bottom to learn the subfield, then follow the See also links to related chapters. Every page has prev / next links and a jump-to-any-chapter menu at the top.

🗺️ The map of AI & ML — 47 chapters

🧮 Mathematical Foundations — linear algebra, calculus, optimization, probability & statistics

🧭 The ML Workflow — what AI/ML is, preparing data, and reducing dimensions

🧩 Classical Machine Learning — regression, classification, ensembles, clustering, evaluation

🎲 Probabilistic Models — graphical models and structured uncertainty

🧠 Deep Learning — neural nets, CNNs, RNNs, transformers, and generative models

🗣️ Applied AI: Vision, Language, Audio & Time — CV, NLP, speech, time series, LLMs, multimodal

🕹️ Reinforcement Learning — learning to act from reward

🛠️ Applied ML Systems & Industries — recommenders, fraud detection, and real-world applications

🚀 Production, Tooling & Infrastructure — MLOps, scaling, and the ML toolkit

📚 Classical & Symbolic AI — search, logic, planning, and evolutionary methods

⚖️ Responsible AI & Frontier — interpretability, causality, ethics, and what is next

🎓 Advanced & Specialized Topics — graph ML, robotics, learning theory, retrieval/data-mining, and building LLMs

🎚️ Post-Training & Fine-Tuning — transfer, PEFT/LoRA/QLoRA, alignment (RLHF/DPO), distillation, and evaluation

🚢 Model Serving & Deployment — MLflow, vLLM, serving frameworks, deployment strategies, monitoring & cost