Skip to Content
03 MathsMml Book

Mathematics for Machine Learning (MML)

Notebook series following the Mathematics for Machine Learning textbook by Deisenroth, Faisal, Ong.

Source PDF: mml-book.pdf

This folder is the best next step after the foundational notebooks if you want structured, rigorous math depth without immediately jumping into research-level theory.

Course Notebooks

#NotebookBook ChapterTopics
01Linear AlgebraCh 2Systems of equations, vector spaces, basis, rank, linear mappings
02Analytic GeometryCh 3Norms, inner products, projections, rotations
03Matrix DecompositionsCh 4Eigenvalues, Cholesky, SVD, low-rank approximation
04Vector CalculusCh 5Gradients, Jacobians, backpropagation, Taylor series
05ProbabilityCh 6Distributions, Bayes’ theorem, Gaussian, exponential family
06OptimizationCh 7Gradient descent, Lagrange multipliers, convexity
07Linear RegressionCh 8-9MLE, MAP, Bayesian linear regression
08PCACh 10Maximum variance, projection, dimensionality reduction
09Gaussian Mixture ModelsCh 11GMM, EM algorithm, latent variables
10Support Vector MachinesCh 12Separating hyperplanes, kernels, dual formulation

Exercises

NotebookContent
Exercises Part 1Practice problems for Ch 2-7
Exercises Part 2Practice problems for Ch 8-12
Solutions Part 1Solutions for Part 1
Solutions Part 2Solutions for Part 2

Prerequisites

Suggested Order

Follow the course notebooks 01-10 in order. The book has two parts:

  • Part I (01-06): Mathematical foundations
  • Part II (07-10): Central ML problems that apply those foundations

How To Use This Folder Well

  • Work in order unless you already know exactly which chapter you need.
  • Treat Part I as the core and Part II as the application payoff for that theory.
  • Use the practice labs when you want the concepts to become more operational.

Practice Labs

For hands-on implementations of each chapter, see practice-labs/.

What Comes Next

Last updated on