Manual companion

Machine Learning labs

Scan a chapter QR (?from=book) or open a lab directly. Enter your email to unlock reader or demo access — then practice in the MVP code loop.

Open learning path Open Adaptly MVP

20chapter labs connected to Adaptly

BookQRLabAdaptly

Reader access

Open the book labs

Book QR links use ?from=book and open reader access after email. Direct visitors can preview the demo path.

01 Operators vs Architects System thinking for machine learning 02 Competitions vs Business Moving from leaderboard thinking to product outcomes 03 Feature Engineering Turning raw data into useful model signal 04 Data Is Geometry Understanding datasets through structure and distance 05 Correlation, Causation, and Why Your Model Lies Leakage, bias, and misleading patterns 06 The Interpretability Problem Explaining model behaviour without pretending certainty 07 Evaluation as a Discipline Evaluation beyond one headline metric 08 Building Systems, Not Demos Production readiness and operational thinking 09 The Modern ML Stack Choosing tools by system responsibility 10 RAG Done Correctly Retrieval as an evaluated system 11 Agent Architectures: Hype vs Reality Safe agent loops and control boundaries 12 Fine-Tuning vs Prompting Cost, quality, and operational trade-offs 13 Quantization and Efficient Inference Latency, throughput, cost, and quality 14 Building Your ML Machine Local, cloud, and hybrid compute choices 15 API Dependence vs Computational Sovereignty Provider risk, routing, and auditability 16 The Math You Actually Need Practical mathematical reasoning for ML engineers 17 The Data Science Layer Data audit before model ambition 18 Competitive Programming and ML Thinking Algorithmic discipline inside ML systems 19 How Big Tech Evaluates Engineers Structured ML system design communication 20 What You Build Next Turning the book into a concrete project path