ML Math Foundations Mastery Path¶

Mastery Path

BOOTCAMP

VINOD BHANUJA

A structured, module-wise course that builds the mathematical foundations behind AI and machine learning from scratch — calculus, linear algebra, and probability & statistics — and shows exactly how each piece underpins the algorithms you'll meet in any ML course: gradient descent, backpropagation, regularization, maximum likelihood, and more. Every idea is developed with real LaTeX formulas, a worked-by-hand numeric example, and a NumPy cross-check, so you never have to take a formula on faith.

How the program is organized¶

Level	Focus	Modules
Level 1 · Entry	Vectors, matrices, derivatives, gradients, linear regression math	9 topics + 1 capstone
Level 2 · Intermediate	Gradient descent, Jacobians/Hessians, eigenvalues, probability basics, Bayes	9 topics + 1 capstone
Level 3 · Advanced	Backpropagation, loss functions, momentum/Adam, regularization, MLE	9 topics + 1 capstone
Level 4 · Master	Convexity, Lagrange multipliers, information theory, logistic regression from scratch	9 topics + 1 capstone

How to use this site¶

Work through each level in order — later modules build on earlier notation and results.
Every topic page pairs a hand-worked derivation with a NumPy cross-check — all you need is pip install numpy. Formulas render as proper LaTeX via MathJax.
Each level ends with a capstone that ties the level's ideas into one worked, numerically-verified example.
Use the search bar (top of the page) to jump straight to a topic.

Start here → Level 1 · Entry

Where to go after this track¶

This site deliberately focuses on the math underneath ML — for the libraries, models, and end-to-end projects built on top of this foundation, see the sibling site: