Mathematics for Machine Learning (MML)¶

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

Source PDF: mml-book.pdf

Course Notebooks¶

#	Notebook	Book Chapter	Topics
01	Linear Algebra	Ch 2	Systems of equations, vector spaces, basis, rank, linear mappings
02	Analytic Geometry	Ch 3	Norms, inner products, projections, rotations
03	Matrix Decompositions	Ch 4	Eigenvalues, Cholesky, SVD, low-rank approximation
04	Vector Calculus	Ch 5	Gradients, Jacobians, backpropagation, Taylor series
05	Probability	Ch 6	Distributions, Bayes’ theorem, Gaussian, exponential family
06	Optimization	Ch 7	Gradient descent, Lagrange multipliers, convexity
07	Linear Regression	Ch 8-9	MLE, MAP, Bayesian linear regression
08	PCA	Ch 10	Maximum variance, projection, dimensionality reduction
09	Gaussian Mixture Models	Ch 11	GMM, EM algorithm, latent variables
10	Support Vector Machines	Ch 12	Separating hyperplanes, kernels, dual formulation

Exercises¶

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

Prerequisites¶

foundational/ notebooks 01-04
Python 3.8+, NumPy, Matplotlib

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

Practice Labs¶

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