1
Front Matter
5 chapters2
Part I: Mathematical and Computational Foundations
6 chapters- Part I: Mathematical and Computational Foundations
- Chapter 1: Linear Algebra for Machine Learning
- Chapter 2: Multivariate Calculus and Optimization
- Chapter 3: Probability Theory and Statistical Inference
- Chapter 4: Information Theory for Data Science — Entropy, KL Divergence, and Why Your Loss Function Works
- Chapter 5: Computational Complexity and Scalability — Knowing What's Possible Before You Start Coding
3
Part II: Deep Learning
10 chapters- Part II: Deep Learning
- Chapter 6: Neural Networks from Scratch
- Chapter 7: Training Deep Networks — Initialization, Batch Normalization, Dropout, Learning Rate Schedules, and the Dark Art of Making It Converge
- Chapter 8: Convolutional Neural Networks — Architecture, Intuition, and Computer Vision Applications
- Chapter 9: Recurrent Networks and Sequence Modeling — RNNs, LSTMs, GRUs, and Their Limitations
- Chapter 10: The Transformer Architecture — Attention Is All You Need (and Why It Changed Everything)
- Chapter 11: Large Language Models — Architecture, Training, Fine-Tuning, RAG, and Practical Applications
- Chapter 12: Generative Models — VAEs, GANs, Diffusion Models, and the Frontier of Data Generation
- Chapter 13: Transfer Learning, Foundation Models, and the Modern Deep Learning Workflow
- Chapter 14: Graph Neural Networks and Geometric Deep Learning — When Your Data Has Structure Beyond Grids and Sequences
4
Part III: Causal Inference
6 chapters- Part III: Causal Inference
- Chapter 15: Beyond Prediction — Why Correlation Isn't Enough and What Causal Inference Offers
- Chapter 16: The Potential Outcomes Framework — Counterfactuals, ATEs, and the Fundamental Problem of Causal Inference
- Chapter 17: Graphical Causal Models — DAGs, d-Separation, and Structural Causal Models
- Chapter 18: Causal Estimation Methods — Matching, Propensity Scores, Instrumental Variables, Difference-in-Differences, and Regression Discontinuity
- Chapter 19: Causal Machine Learning — Heterogeneous Treatment Effects, Uplift Modeling, and Double Machine Learning
5
Part IV: Bayesian and Temporal Data Science
5 chapters- Part IV: Bayesian and Temporal Data Science
- Chapter 20: Bayesian Thinking — Priors, Posteriors, and Why Frequentist vs. Bayesian Is the Wrong Debate
- Chapter 21: Bayesian Modeling in Practice — PyMC, Hierarchical Models, and When Bayesian Methods Earn Their Complexity
- Chapter 22: Bayesian Optimization and Sequential Decision-Making — From Hyperparameter Tuning to Bandits
- Chapter 23: Advanced Time Series and Temporal Models — State-Space Models, Temporal Fusion Transformers, and Probabilistic Forecasting
6
Part V: Production ML Systems
8 chapters- Part V: Production ML Systems
- Chapter 24: ML System Design — Architecture Patterns for Real-World Machine Learning
- Chapter 25: Data Infrastructure — Feature Stores, Data Warehouses, Lakehouses, and the Plumbing Nobody Teaches
- Chapter 26: Training at Scale — Distributed Training, GPU Optimization, and Managing Compute Costs
- Chapter 27: ML Pipeline Orchestration — Airflow, Dagster, Prefect, and Designing Robust Data Workflows
- Chapter 28: ML Testing and Validation Infrastructure — Data Contracts, Behavioral Testing, and Great Expectations
- Chapter 29: Continuous Training and Deployment — CI/CD for ML, Canary Deployments, Shadow Mode, and Progressive Rollout
- Chapter 30: Monitoring, Observability, and Incident Response — Keeping ML Systems Healthy in Production
7
Part VI: Responsible and Rigorous Data Science
6 chapters- Part VI: Responsible and Rigorous Data Science
- Chapter 31: Fairness in Machine Learning — Definitions, Impossibility Results, Mitigation Strategies, and Organizational Practice
- Chapter 32: Privacy-Preserving Data Science — Differential Privacy, Federated Learning, and Synthetic Data
- Chapter 33: Rigorous Experimentation at Scale — Multi-Armed Bandits, Interference Effects, and Experimentation Platforms
- Chapter 34: Uncertainty Quantification — Calibration, Conformal Prediction, and Knowing What Your Model Doesn't Know
- Chapter 35: Interpretability and Explainability at Scale — From SHAP to Concept-Based Explanations in Production
8
Part VII: Leadership and Synthesis
5 chapters- Part VII: Leadership and Synthesis
- Chapter 36: Capstone — Designing, Building, and Governing a Production Recommendation System
- Chapter 37: Reading Research Papers — How to Stay Current, Evaluate Claims, and Separate Signal from Hype
- Chapter 38: The Staff Data Scientist — Technical Leadership, Mentoring, Strategy, and Shaping the Roadmap
- Chapter 39: Building and Leading a Data Science Organization — Hiring, Team Structure, Culture, and Scaling Impact
9
Appendices
13 chapters- Glossary
- Answers to Selected Exercises
- Bibliography
- Appendix A: Mathematical Notation Reference
- Appendix B: PyTorch API Reference
- Appendix C: Python ML Ecosystem Reference
- Appendix D: Environment Setup
- Appendix E: Dataset Catalog
- Appendix F: SQL and Infrastructure Reference
- Appendix G: Evaluation Metrics Reference
- Appendix H: ML System Design Patterns
- Appendix I: Key Papers and Reading Lists
- Appendix J: Causal Inference Identification Guide
Explore Related Books
More open-access textbooks from our library
Advanced COBOL 40 chapters · ~67h AI Ethics 39 chapters · ~82h AI Literacy 21 chapters · ~27h AI & ML for Business 40 chapters · ~80h AI Engineering 40 chapters · ~53h Algorithmic Addiction 40 chapters · ~71h American Government 40 chapters · ~77h Applied Psychology 40 chapters · ~52h Assembly Language 40 chapters · ~27h Blockchain & Crypto 40 chapters · ~68h Calculus 40 chapters · ~51h Automotive Sales 40 chapters · ~73h College Football Analytics 28 chapters · ~18h Creator Economy 41 chapters · ~57h Pattern Recognition 43 chapters · ~92h Cybersecurity 40 chapters · ~84h Digital Forensics 40 chapters · ~69h Data & Society 40 chapters · ~72h Data Viz with Python 35 chapters · ~52h Discrete Mathematics 40 chapters · ~75h Ethical Hacking 41 chapters · ~58h Fandom 44 chapters · ~70h Forensic Science 40 chapters · ~74h Grant Writing 35 chapters · ~36h History of Appalachia 42 chapters · ~69h How Humans Get Stuck 40 chapters · ~36h Handling Confrontation 40 chapters · ~80h How to Learn Anything 38 chapters · ~54h How Your House Works 40 chapters · ~66h IBM DB2 37 chapters · ~53h Insurance Underwriting 40 chapters · ~71h Intermediate COBOL 54 chapters · ~44h Intermediate Data Science 36 chapters · ~39h Intro CS Python 27 chapters · ~28h Intro to Data Science 36 chapters · ~55h Introductory Economics 40 chapters · ~28h Introductory Statistics 28 chapters · ~48h Learning COBOL 42 chapters · ~64h Prediction Markets 42 chapters · ~60h Linear Algebra 40 chapters · ~60h Metacognition 28 chapters · ~52h Media Literacy 41 chapters · ~80h Music Production 40 chapters · ~84h NFL Analytics 28 chapters · ~16h Nuclear Physics 35 chapters · ~60h Organic Chemistry 40 chapters · ~43h Pascal Programming 40 chapters · ~43h Photography 40 chapters · ~85h Physics of Music 48 chapters · ~75h Political Analytics 41 chapters · ~67h Popular Psychology 40 chapters · ~21h Practical Philosophy 38 chapters · ~63h Basketball Analytics 31 chapters · ~30h Soccer Analytics 30 chapters · ~43h Propaganda 40 chapters · ~80h Python for Business 40 chapters · ~40h Quantum Mechanics 40 chapters · ~66h RegTech 40 chapters · ~59h The Science of Cooking 40 chapters · ~70h Science of Seduction 45 chapters · ~60h Sports Betting 42 chapters · ~63h Database Fundamentals 40 chapters · ~34h Technical Writing 40 chapters · ~70h Architecture of Surveillance 40 chapters · ~54h Science of Luck 40 chapters · ~72h Eastern Cultures 40 chapters · ~47h Western Culture 40 chapters · ~30h Vibe Coding 42 chapters · ~58h Video Game Design 40 chapters · ~77h Why They Watch 40 chapters · ~48h Working with AI 42 chapters · ~58h