"The best way to learn a complex technology is not to study it in isolation, but to build something real with it, then understand why it works."
Tensor, Pragmatically Curious AI Agent
Overview of the Front Matter
Before you build anything, you need a map. This front matter orients you before you dive into the technical chapters. It answers four questions every reader has at the start: What does this book cover, and who is it for? How should I navigate 39 chapters and 11 parts given my background and goals? How can an instructor build a university course from this material? And what conventions, callout types, and recurring elements will I encounter on every page?
Whether you plan to read cover to cover or jump straight to the chapters that match your role, spending 15 minutes here will save you hours of backtracking later. Each section below links to a dedicated page with full detail.
This front matter is your map to the entire book. Investing a few minutes here will help you choose the right reading path for your background, understand the conventions used in every chapter, and see how the 11 parts connect into a coherent journey from foundations to production-ready AI systems.
Sections
- FM.0a About the Authors Alexander (Sasha) Apartsin, Ph.D. and Yehudit Aperstein, Ph.D.: backgrounds, research, and teaching experience.
- FM.0b About This Book Who should read this book, book structure overview, and how the collaborative human-AI production process works.
- FM.1 What This Book Covers The eleven parts and their dependencies, what makes this book different, and what it does not cover.
- FM.2 Who Should Read This Book Primary and secondary audiences, assumed background, personalized pathways, and 2024 through 2026 novelty coverage.
- FM.3 How to Use This Book: Conventions, Callouts & Labs The four-phase pedagogical approach (concept, intuition, code, production), callout types (Big Picture, Key Insight, Warning, Fun Note, Research Frontier), code conventions, lab exercises, and how to get started based on your background.
- FM.4 Problem-Solution Key A detailed lookup table mapping common NLP, ML, and AI engineering tasks to the specific chapters and sections that solve them, with one-liner examples for each task.
- FM.5 Reading Pathways Twenty self-study pathways tailored to different roles and backgrounds: engineers, researchers, data scientists, product builders, educators, and more. Each with chapter guides, time estimates, and difficulty levels.
- FM.6 Course Syllabi Four complete 14-week university syllabi (undergraduate and graduate, engineering and research) plus five specialty tracks, each with week-by-week schedules, assignments, and hyperlinked chapter references.
- FM.7 How This Book Was Created The AI-assisted production pipeline, agent team structure and roles, the quality process, the human role in oversight and direction, and why building this book is itself a case study in the AI patterns it teaches.
- FM.8 The Wisdom Council Meet the 42 AI commentators who share wisdom, warnings, and wit through the book's epigraphs. Each profile card shows the character's expertise, personality, and the topics they comment on.
- FM.9 The Writing Team The full roster of specialized AI agents that collaboratively wrote, reviewed, and refined this book, organized by function: leadership, pedagogy, content quality, style, visual/creative, and publication QA.
What Comes Next
After reading the front matter, proceed to Chapter 00: ML & PyTorch Foundations if you are reading sequentially, or use the Reading Pathways to find your ideal starting point.