Mathematics for AI | Zahra Amini

The Mathematics for AI course at Hobot Academy provides the essential mathematical foundations required to truly understand and build modern Artificial Intelligence systems. Rather than treating AI as a black box, this curriculum focuses on the “Math-to-Code” approach, deriving formulas theoretically and implementing them algorithmically.

Instructor: Zahra Amini

Instead of duplicating the materials here, the full curriculum, mathematical proofs, and NumPy implementations are maintained directly on the official repository.

🚀 VIEW FULL COURSE & NOTEBOOKS ON GITHUB

Course Syllabus

The repository covers the four fundamental pillars of AI mathematics, structured into intensive phases:

Phase 1: Linear Algebra & Matrix Mechanics
- Vectors, Matrices, Matrix Inversion, and Decompositions.
- Eigenvalues, Eigenvectors, and PCA (Principal Component Analysis) implementation from scratch.
Phase 2: Calculus & Optimization
- Derivatives, Critical Points, and Jacobians.
- Mechanics of Gradient Descent and Multiple Regression.
Phase 3: Probability & Bayesian Theory
- Probability Fundamentals and conditional logic.
- Logistic Regression logic, Naive Bayes Classifier, and Bayesian Filtering.
Phase 4: Statistics & Data Distributions
- Expectations, Variances, and the Normal Distribution.
- Descriptive Statistics for data storytelling.

📚 Acknowledgments & References

Education is a collaborative journey. I firmly believe in academic integrity and referencing foundational works.

Parts of the pedagogical structure and curated materials in this repository are inspired by and adapted from the IE 300: Analysis of Data course by Professor George Vogiatzis at the University of Illinois (Urbana-Champaign).

🔗 Source: vogiatzis.web.illinois.edu/ie300.html

👩‍🏫 Instructor: Zahra Amini

GitHub Logo GitHub

Portfolio Logo Portfolio