A comprehensive, self-contained introduction to machine learning that blends intuition, mathematics, and runnable code.

Welcome to Machine Learning: From Foundations to Deep Learning.

A comprehensive, self-contained introduction to machine learning that blends intuition, mathematics, and runnable code. The book starts from the question "what does it mean for a machine to learn?" and builds steadily up to modern deep learning, including the Transformer architecture that powers today's large language models.

This title is part of the ShriIra library and is free to read in full, right here — our small contribution to making world-class knowledge easy to reach.

A note on reading it: open the Contents menu at the top of the reader to jump between chapters, use the Aa menu to set a comfortable text size, theme (light, sepia, or night), and single- or two-page layout. Your place is saved automatically, so you can always pick up where you left off.

We hope it serves you well.

— Shriira Press

Contents

1. Chapter 1 — What Is Machine Learning?
2. Chapter 2 — Mathematical Foundations
3. Chapter 3 — The Learning Problem
4. Chapter 4 — Linear Regression
5. Chapter 5 — Classification and Logistic Regression
6. Chapter 6 — Optimization and Gradient Descent
7. Chapter 7 — Regularization and Model Selection
8. Chapter 8 — Decision Trees and Ensemble Methods
9. Chapter 9 — Support Vector Machines and Kernels
10. Chapter 10 — Clustering and Dimensionality Reduction
11. Chapter 11 — Neural Networks and Backpropagation
12. Chapter 12 — Deep Learning Architectures
13. Chapter 13 — Building Real Systems
14. Appendix A — Notation and Symbols
15. Appendix B — Further Reading