Mathematical Foundations of Machine Learning

This repository contains slides, notes, and (optional) notebooks for the Mathematical Foundations of Machine Learning mini-course taught by Gabriel Wendell Celestino Rocha.

📚 About the Course

This is a theoretical course focused exclusively on the mathematical principles of modern Machine Learning. It covers:

• Linear Algebra
• Probability and Information Theory
• Optimization
• Statistical Learning Theory
• Core ML models (regression, classification, PCA, etc.)
• Theoretical insights into Neural Networks and Generalization

Important: This is not a course on ML programming or implementation.

🗓️ Course Schedule

See the full schedule for detailed day-by-day topics.

📁 Structure

• Slides/ — Lecture slides
• Notes/ — Class notes with formal definitions, theorems, and proofs
• Notebooks/ — Optional illustrative Jupyter notebooks
• References/ — Recommended readings and bibliography

🧠 Instructor

Gabriel Wendell Celestino Rocha, Physics Department — UFRN

---

Feel free to contribute suggestions via Issues or Pull Requests!